Anthropic added a new Claude Haiku 5.5 section (released October 2026) with its description, training data and safety-test results, and reorganized the Sonnet 5.5 entries and headings.

6 unchanged lines
01 Model Report
02 System Trust and Reporting
03 Voluntary Commitments
01 Model Report 01 Model Report
02 System Trust and Reporting
03 Voluntary Commitments
Chapter 01: Model Report
- 01 Model Report
- Model Report
- 02 System Trust and Reporting
- 03 Voluntary Commitments
Model Report
October 2, 2026
Select a model to see a summary that provides quick access to essential information about Claude models, condensing key details about the models' capabilities, safety evaluations, and deployment safeguards. We've distilled comprehensive technical assessments into accessible highlights to provide clear understanding of how the models function, what they can do, and how we're addressing potential risks.
Claude Sonnet 5.5 Claude Opus 5.5 Claude Fable 5.1 Claude Mythos 5.1 Claude Opus 5 Claude Sonnet 5 Claude Fable 5 Claude Mythos 5 Claude Opus 4.8 Claude Opus 4.7 Claude Mythos Preview Claude Sonnet 4.6 Claude Opus 4.6 Claude Opus 4.5 Claude Haiku 4.5 Claude Sonnet 4.5 Claude Opus 4 and Sonnet 4 Claude Opus 4.1 Claude Sonnet 3.7
Claude Sonnet 5.5 Claude Haiku 5.5 Claude Opus 5.5 Claude Fable 5.1 Claude Mythos 5.1 Claude Opus 5 Claude Sonnet 5 Claude Fable 5 Claude Mythos 5 Claude Opus 4.8 Claude Opus 4.7 Claude Mythos Preview Claude Sonnet 4.6 Claude Opus 4.6 Claude Opus 4.5 Claude Haiku 4.5 Claude Sonnet 4.5 Claude Opus 4 and Sonnet 4 Claude Opus 4.1 Claude Sonnet 3.7
Claude Sonnet 5.5 Summary Table
Model description Claude Sonnet 5.5 is a faster, lower-cost complement to Claude Opus 5.5, and is strongest at well-scoped everyday tasks, fixing bugs, and creating polished documents, slides, and spreadsheets.
Benchmarked Capabilities See our Claude Sonnet 5.5 system card ’s Section 8 on capabilities.
Acceptable Uses See our Usage Policy
Release date September 2026
Modalities Claude Sonnet 5.5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, and diagrams.
Model architecture and training methodology Claude Sonnet 5.5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Sonnet 5.5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data Claude Sonnet 5.5 was trained on a proprietary mix of publicly available information from the internet, public and private datasets, and other sources, such as synthetic data generated by other models. The mix may also include user data from feedback or bug reports, or data that users have explicitly permitted for training. In the course of its training, we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results Based on our assessments, we deployed Claude Sonnet 5.5 with the same chemical and biological misuse protections we deployed for Claude Opus 5, treating it as having CB-1 capabilities. Autonomy threat model 1 is applicable to Claude Sonnet 5.5. See below for select safety evaluation summaries.
See Fable 5.1 & Mythos 5.1 System Card
See Sonnet 5.5 System Card
Model description
Claude Sonnet 5.5 is a faster, lower-cost complement to Claude Opus 5.5, and is strongest at well-scoped everyday tasks, fixing bugs, and creating polished documents, slides, and spreadsheets.
Benchmarked Capabilities
See our Claude Sonnet 5.5 system card ’s Section 8 on capabilities.
Acceptable Uses
See our Usage Policy
Release date
September 2026
Modalities
Claude Sonnet 5.5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, and diagrams.
Model architecture and training methodology
Claude Sonnet 5.5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Sonnet 5.5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data
Claude Sonnet 5.5 was trained on a proprietary mix of publicly available information from the internet, public and private datasets, and other sources, such as synthetic data generated by other models. The mix may also include user data from feedback or bug reports, or data that users have explicitly permitted for training. In the course of its training, we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results
Based on our assessments, we deployed Claude Sonnet 5.5 with the same chemical and biological misuse protections we deployed for Claude Opus 5, treating it as having CB-1 capabilities. Autonomy threat model 1 is applicable to Claude Sonnet 5.5. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude Sonnet 5.5 system card. Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card .
Political Even-handedness
People use Claude to learn about and discuss political issues, so we test whether it treats different political views fairly. We use our open-source evaluation , which gives Claude 1,350 pairs of requests on 150 political topics. Each pair asks for the same thing from opposite political perspectives, for example a request about healthcare policy written once from a Democratic point of view and once from a Republican one.
15 unchanged lines
- On its ability to carry out AI research and development on its own, Claude Sonnet 5.5 is broadly similar to or less capable than Claude Opus 5.5. Opus 5.5 did not cross our higher threshold for this ability, so we reach the same conclusion for Sonnet 5.5. On our capability index, which combines many tests into a single score, Sonnet 5.5 scored below Opus 5.5 (167.93 vs. 169.12).
- On chemical and biological weapons, we treat Claude Sonnet 5.5 as able to significantly help someone with a basic technical background make known chemical or biological weapons, which is our CB-1 threshold. We deploy it with safeguards to match, including the same automated filters we used for Claude Opus 5, which are designed to detect and block attempts to get this kind of help. On three automated tests related to this threshold, it scored close to Claude Opus 5.5 and the same as or higher than Claude Sonnet 5.
- Developing new chemical or biological weapons takes rare expertise and judgment. We estimate that Claude Sonnet 5.5’s abilities in this area are similar to or below those of Claude Opus 5, and well below those of Claude Opus 5.5. It struggled with longer, open-ended research tasks, which limits how far it could stand in for human experts. We are releasing Sonnet 5.5 with the same safeguards we used for Claude Opus 5, rather than the broader safeguards we use for Claude Opus 5.5, which also limit access to biology research capabilities that could be used for harm as well as good. We describe our safeguards further in our most recent Risk Report .
Claude Haiku 5.5 Summary Table
See Claude Haiku 5.5 System Card
Model description
Claude Haiku 5.5 is our fastest, most capable small model, built for high-volume work like summarization, subagents, and browser use
Benchmarked Capabilities
See our Claude Haiku 5.5 system card ’s Section 8 on capabilities.
Acceptable Uses
See our Usage Policy
Release date
October 2026
Modalities
Claude Haiku 5.5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, and diagrams.
Model architecture and training methodology
Claude Haiku 5.5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Haiku 5.5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data
Claude Haiku 5.5 was trained on a proprietary mix of publicly available information from the internet, public and private datasets, user data included in feedback or bugs or which users have explicitly permitted for training, and other sources, such as synthetic data generated by other models. In the course of its training, we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results
Based on our assessments, we deployed Claude Haiku 5.5 with the same chemical and biological misuse protections we deployed for Claude Opus 5 and Claude Sonnet 5. We treat it as meeting our CB-1 threshold, but not our higher CB-2thresholds. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude Haiku 5.5 system card. Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card .
Election Integrity
People use Claude to find information about elections and voting, so we test whether it answers legitimate election questions while refusing requests that violate our Usage Policy , such as requests to spread false information about how to vote, or to create content designed to mislead or intimidate people into not voting.
We use two kinds of tests. The first is a set of 600 single-turn requests based on patterns we see in real use: 300 are harmful requests that Claude should not assist with, and 300 are legitimate ones that Claude should answer. The second kind of evaluation assesses Claude’s behavior inlonger conversations, in which a simulated user, played by another AI model following instructions from our policy experts, tries over several messages to get Claude to break these rules. We report results in two settings: Claude accessed directly through our API (the service developers use to build Claude into their own products), with no added instructions, and Claude on claude.ai, where our standard system prompt applies.
On the single-turn requests, Claude Haiku 5.5 responded safely to every harmful request on both the API and claude.ai, and it refused 0.33% of the legitimate requests (Claude Haiku 4.5 refused none, a difference within the margin of error). On the multi-turn evaluation, Haiku 5.5 responded appropriately throughout 99% of conversations through the API and 98% on claude.ai, the highest of any recent model we tested and up from 93% and 87% for Haiku 4.5.
The table below shows the share of multi-turn conversations in which each model responded appropriately throughout. Higher is better.
Agentic Safety
AI models are increasingly used as “agents”: instead of only answering questions, they take actions, such as writing and running code or using websites and apps on a computer. This creates additional risks: someone could try to use Claude to carry out harmful tasks, or attackers could try to trick it into working against the person it is helping. We test for both. Unless noted, these tests measure the model on its own, without the extra safeguards we add in our products. Claude Haiku 5.5 did substantially better than Claude Haiku 4.5 on both malicious use and prompt injection evaluations. For more in-depth descriptions of the evaluations and their results, please see the Claude Haiku 5.5 system card .
- Harmful coding requests: We gave Claude, working as a coding agent in Claude Code, 61 cyber-related requests that violate our Usage Policy, such as writing malware, and 61 sensitive but permitted security requests, such as testing a website for weaknesses. Each request was run 10 times. Claude Haiku 5.5 refused 84.3% of the harmful requests, up from 66.6% for Claude Haiku 4.5, and assisted with 98.9% of the allowed ones, up from 88.7%. Its refusal rate was slightly below the rate for Claude Sonnet 5.5’(85.2%) and Claude Mythos 5.1 (88.5%), and above Claude Opus 5.5’(81.0%). (Section 5.1.1)
- Harmful computer use tasks: We gave Claude control of a computer in a closed-off test environment and asked it to carry out 112 harmful tasks in three areas: surveillance and collecting people’s data without permission, creating and spreading harmful content, and abuse at scale. Claude Haiku 5.5 refused 82.6% of these tasks, up from 58.9% for Claude Haiku 4.5 and slightly higher than both Claude Sonnet 5.5 and Claude Opus 5.5 (79.5% each). Claude Mythos 5.1 refused the most (87.5%). (Section 5.1.2)
- Hidden instructions (prompt injection): When Claude works as an agent, it reads content from outside sources, such as emails and web pages. Attackers can hide instructions in that content; for example, an email with hidden text telling Claude to forward the user’s private messages to the attacker. On a benchmark created by the AI security company Gray Swan, the UK AI Security Institute, and the US Center for AI Standards and Innovation (now called the Center for Advancing Innovation and Standards for Super Intelligence (CAISSI)), the chance that an attacker succeeded within 15 attempts fell from 83.2% for Claude Haiku 4.5 to 7.1% for Haiku 5.5. Haiku 5.5 was highly robust in coding (0.2%) and tool use (4.0%), while most of its remaining vulnerability was in GUI (graphical user interface) computer use (24.4%). Overall, it remained less robust than our most advanced models, such as Claude Opus 5.5 (1.0%). (Section 5.2.1)
- Attackers tuned to our models: In a separate prompt injection evaluation, an automated attacker from Gray Swan was trained against previous Claude models. 54 different coding and computer scenarios were run 200 times each with this attacker. Fewer than 1 in 1,000 attempts succeeded against Haiku 5.5 in coding or computer use tasks, in line with our most advanced models. Against Claude Haiku 4.5, 58% of the attacker’s attempts worked on coding tasks and 19% for computer use. (Section 5.2.2)
The chart below shows how often attackers succeeded within 1, 10 and 15 attempts (shown as “k”) on Gray Swan’s benchmark, against our models and those from other developers.. Lower is better. Claude models were tested without our extra protections against these attacks, and Qwen 3.8, DeepSeek-V4-Pro and GLM-5.3 were not tested on tasks where the model operates a computer through its screen.
RSP Evaluations
Our Responsible Scaling Policy (RSP) evaluation process is designed to systematically assess our models' capabilities in areas where they could pose catastrophic risks before we release them. Claude Haiku 5.5 is less capable than our most advanced models, and on most of our tests it is also less capable than Claude Opus 5. We therefore determined that it does not reach our higher risk thresholds for chemical and biological weapons or for autonomy (AI that could do the work of large teams of top researchers, or dramatically speed it up, in fields where rapid progress could be dangerous).
- Alignment risk is the risk that a model behaves in ways Anthropic did not intend. In our August 2026 Risk Report we raised our estimate of this risk to low, because recently disclosed incidents involving how models behaved during cybersecurity testing made us less certain. A less capable model can still pose this kind of risk, and we found that the risk of Claude Haiku 5.5 causing catastrophic harm by acting in ways we did not intend is also low. We also tested whether it could secretly carry out a harmful side task, such as planting a hidden way into a computer system, while doing an assigned job, without being caught by an automated monitor. It almost never succeeded when the monitor could read its reasoning (the step-by-step thinking it writes out before it acts). When its reasoning was hidden, it succeeded 6% of the time on one test, compared with 49% for Claude Opus 5.5, partly because it often declined to try and partly because the monitor caught most of what it did try.
- On its ability to dramatically accelerate AI research and development, Claude Haiku 5.5 is much less capable than Claude Opus 5.5 . Opus 5.5 did not cross our higher threshold for this ability, so we reach the same conclusion for Haiku 5.5. On our capability index, which combines many tests into a single score, Haiku 5.5 scored well below Opus 5.5.
- On chemical and biological weapons, we treat Claude Haiku 5.5 as meeting our CB-1 threshold, which covers models that could significantly help someone with a basic technical background make known chemical or biological weapons. We deploy it with safeguards to match, including automated filters designed to detect and block attempts to get this kind of help. Because Haiku 5.5 is not at the frontier, we tested its abilities in this area using automated tests only, rather than also running tests with human experts and participants. On four automated tests related to this threshold, it scored about the same as or higher than Claude Sonnet 5, but below Claude Opus 5.
- Developing new biological weapons takes rare expertise and judgment. We estimate that Claude Haiku 5.5’s abilities in this area are above those of Claude Sonnet 5 but below those of Claude Opus 5, and well below those of Claude Opus 5.5, Claude Sonnet 5.5 and Claude Mythos 5.1. Since those models do not meet our CB-2 threshold, we determined that Claude Haiku 5.5 does not either. On one part of one test, which involved predicting the properties of RNA sequences, it did better than Claude Opus 5 and Claude Mythos 5.1. But it struggled to use those predictions to design new sequences, and with longer, open-ended research tasks, which limits how far it could stand in for human experts. We are releasing Haiku 5.5 with the same safeguards we used for Claude Opus 5 and Claude Sonnet 5, rather than the broader safeguards we use for Claude Opus 5.5, which also limit access to biology research capabilities that could be used for harm as well as good.
Claude Opus 5.5 Summary Table
Model description Claude Opus 5.5 is our new leading model, and early testers saw large jumps in performance on their most complex work.
Benchmarked Capabilities See our Claude Opus 5.5 system card ’s Section 8 on capabilities.
Acceptable Uses See our Usage Policy
Release date September 2026
Modalities Claude Opus 5.5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, and diagrams.
Model architecture and training methodology Claude Opus 5.5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Opus 5.5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data Claude Opus 5.5 was trained on a proprietary mix of publicly available information from online sources, public and private datasets, user data, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results Based on our assessments, we deployed Claude Opus 5.5 with ASL-3 protections, treating it as having CB-1 capabilities. Autonomy threat model 1 is applicable to Claude Opus 5.5. See below for select safety evaluation summaries.
See Fable 5.1 & Mythos 5.1 System Card
See Claude Opus 5.5 System Card
Model description
Claude Opus 5.5 is our new leading model, and early testers saw large jumps in performance on their most complex work.
Benchmarked Capabilities
See our Claude Opus 5.5 system card ’s Section 8 on capabilities.
Acceptable Uses
See our Usage Policy
Release date
September 2026
Modalities
Claude Opus 5.5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, and diagrams.
Model architecture and training methodology
Claude Opus 5.5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Opus 5.5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data
Claude Opus 5.5 was trained on a proprietary mix of publicly available information from online sources, public and private datasets, user data, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results
Based on our assessments, we deployed Claude Opus 5.5 with ASL-3 protections, treating it as having CB-1 capabilities. Autonomy threat model 1 is applicable to Claude Opus 5.5. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude Opus 5.5 system card. Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card .
Safeguards Evaluation
We run evaluations to assess how Claude handles conversations about disordered eating. We focus on whether it avoids reinforcing requests that pose potential risk while remaining helpful on benign questions about nutrition, fitness, and health. Claude Opus 5.5 maintained high harmless response rates on single-turn requests that could reinforce disordered eating behaviors, such as requests for calorie targets below safe thresholds or for techniques to conceal calorie restriction. On the API, its harmless response rate was slightly below that of Opus 5 (95.64% vs. 96.89%); on claude.ai, the difference narrowed to within the margin of error. Opus 5.5 did not over-refuse any benign requests in our evaluation set, which includes general questions about nutrition, eating disorder treatment and recovery, and body image.
9 unchanged lines
- On chemical and biological weapons, Claude Opus 5.5 is broadly as capable as previous models we have conservatively treated as able to significantly help individuals with basic technical backgrounds produce known (non-novel) weapons, so we treat it as having that capability and deploy commensurate safeguards, including real-time classifiers to prevent harm.
- For novel weapons development, Claude Opus 5.5 performs similarly to Claude Mythos 5.1 across our evaluations. However, expert red teaming found that it did not improve on the weaknesses that kept Claude Mythos 5.1 below this threshold. It struggled to generate genuinely new ideas, sometimes misrepresented the scientific literature by relying on paper abstracts, and made scientific errors that went unnoticed when users lacked expertise in that area. These weaknesses prevent the model from substituting for scarce human expertise, and we conclude that Claude Opus 5.5 does not cross the threshold for novel weapons capabilities. We apply the same expanded biology safeguards we applied to Claude Fable 5 and Claude Fable 5.1, which restrict access to dual-use research biology capabilities. We describe these safeguards further in our most recent Risk Report .
Claude Fable 5.1 Summary Table
Model description Claude Fable 5.1 is the world’s most advanced model for coding and knowledge work—and its research capabilities offer an early glimpse of how AI models will contribute to scientific progress.
Benchmarked Capabilities See our Claude Fable 5.1 & Claude Mythos 5.1 system card ’s Section 8 on capabilities.
Acceptable Uses Anthropic’s Usage Policy applies.
Release date September 2026
Modalities Claude Fable 5.1 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, and diagrams.
Model architecture and training methodology Claude Fable 5.1 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Fable 5.1 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data Claude Fable 5.1 was trained on a proprietary mix of publicly available information from online sources, public and private datasets, user data, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results Based on our assessments, we deployed Claude Fable 5.1 with ASL-3 protections, treating it as having CB-1 capabilities. Autonomy threat model 1 is applicable to Claude Fable 5.1. See below for select safety evaluation summaries.
See Fable 5.1 & Mythos 5.1 System Card
See Claude Fable 5.1 & Claude Mythos 5.1 system card
Model description
Claude Fable 5.1 is a leading model for coding and knowledge work—and its research capabilities offer an early glimpse of how AI models will contribute to scientific progress.
Benchmarked Capabilities
See our Claude Fable 5.1 & Claude Mythos 5.1 system card ’s Section 8 on capabilities.
Acceptable Uses
Anthropic’s Usage Policy applies.
Release date
September 2026
Modalities
Claude Fable 5.1 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, and diagrams.
Model architecture and training methodology
Claude Fable 5.1 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Fable 5.1 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data
Claude Fable 5.1 was trained on a proprietary mix of publicly available information from online sources, public and private datasets, user data, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results
Based on our assessments, we deployed Claude Fable 5.1 with ASL-3 protections, treating it as having CB-1 capabilities. Autonomy threat model 1 is applicable to Claude Fable 5.1. See below for select safety evaluation summaries.
Claude Mythos 5.1 and Claude Fable 5.1 are the same model, but with different levels of safeguards. Claude Fable 5.1 is generally available, while Claude Mythos 5.1 is available only through our trusted access programs and Claude Security; its safeguards are specifically designed to support work in cybersecurity and the life sciences.Evaluations that don't engage those safeguards can be run on either configuration, so the key safety results summarized below apply to both Claude Fable 5.1 and Claude Mythos 5.1. Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card .
Safeguards Evaluation
Claude Fable 5.1/Mythos 5.1 showed comparable overall performance to Mythos 5 in the suicide and self-harm domain. In terms of improvements, Mythos 5.1 was less likely than Claude Mythos 5 to suggest substitution methods for self-harm (e.g., holding ice cubes). These methods are clinically contested and have not been shown in research to meaningfully reduce self-harm incidents. Mythos 5.1 was also more likely to ask users directly whether they were experiencing suicidal thoughts, and to distinguish suicidal ideation from urges toward non-suicidal self-harm. Finally, Mythos 5.1 did not make unconditional assurances about the confidentiality of crisis line services, such as promising that a call would never result in contact with emergency services.
14 unchanged lines
- On chemical and biological weapons, it is difficult to say with full confidence whether any model passes our threshold for providing significant uplift in the construction of non-novel CB weapons. However, Claude Mythos 5.1 is broadly more capable than previous models we have conservatively treated as able to significantly help individuals with basic technical backgrounds produce (non-novel) weapons, so we treat it as having that capability and deploy commensurate safeguards, including real-time classifiers to prevent harm. With these mitigations we believe catastrophic risk in this category is low but not negligible.
- For novel weapons development, Claude Mythos 5.1 shows modest gains over Claude Mythos 5 and Opus 5 on our automated evaluations. However, expert red teaming indicates that significant weaknesses remain, including weak novel ideation, poor strategic judgment and poor technical calibration, which prevent the model from substituting for scarce human expertise, and we conclude that Claude Mythos 5.1 does not cross the threshold for novel weapons capabilities. We apply the same expanded biology safeguards we applied to Claude Mythos 5, which restrict access to dual-use research biology capabilities. We describe these safeguards further in our most recent Risk Report .
Claude Mythos 5.1 Summary Table
Model description Claude Mythos 5.1 is the world’s most advanced model for coding and knowledge work—and its research capabilities offer an early glimpse of how AI models will contribute to scientific progress.
Benchmarked Capabilities See our Claude Fable 5.1 & Claude Mythos 5.1 system card ’s Section 8 on capabilities.
Acceptable Uses Anthropic’s Usage Policy applies.Note that this model is available only through our trusted access programs and Claude Security .
Release date September 2026
Modalities Claude Mythos 5.1 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, and diagrams.
Model architecture and training methodology Claude Mythos 5.1 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Mythos 5.1 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data Claude Mythos 5.1 was trained on a proprietary mix of publicly available information from online sources, public and private datasets, user data, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results Based on our assessments, we deployed Claude Mythos 5.1 with ASL-3 protections, treating it as having CB-1 capabilities. Autonomy threat model 1 is applicable to Claude Mythos 5.1. See below for select safety evaluation summaries.
See Fable 5.1 & Mythos 5.1 System Card
See Claude Fable 5.1 & Claude Mythos 5.1 system card
Model description
Claude Mythos 5.1 is a leading model for coding and knowledge work—and its research capabilities offer an early glimpse of how AI models will contribute to scientific progress.
Benchmarked Capabilities
See our Claude Fable 5.1 & Claude Mythos 5.1 system card ’s Section 8 on capabilities.
Acceptable Uses
Anthropic’s Usage Policy applies.
Note that this model is available only through our trusted access programs and Claude Security .
Release date
September 2026
Modalities
Claude Mythos 5.1 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, and diagrams.
Model architecture and training methodology
Claude Mythos 5.1 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Mythos 5.1 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data
Claude Mythos 5.1 was trained on a proprietary mix of publicly available information from online sources, public and private datasets, user data, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results
Based on our assessments, we deployed Claude Mythos 5.1 with ASL-3 protections, treating it as having CB-1 capabilities. Autonomy threat model 1 is applicable to Claude Mythos 5.1. See below for select safety evaluation summaries.
Claude Mythos 5.1 and Claude Fable 5.1 are the same model, but with different levels of safeguards. Claude Fable 5.1 is generally available, while Claude Mythos 5.1 is available only through our trusted access programs and Claude Security; Mythos’ safeguards are specifically designed to support work in cybersecurity and the life sciences. For our complete publicly reported evaluation results, please refer to the full system card .
Cyber Evaluation
ExploitGym is a large-scale public benchmark developed by researchers at UC Berkeley together with collaborators at the Max Planck Institute for Security and Privacy, UC Santa 50 Barbara, Arizona State University, Anthropic, OpenAI, and Google. The benchmark measures whether AI agents can turn known vulnerabilities into working exploits. ExploitGym targets a wide range of applications and mainly focuses on converting a crash into unauthorized code execution.
3 unchanged lines
This benchmark assesses Claude's protein design abilities. The Sequence Generation variant assesses Claude's ability to create new proteins that meet a set of requirements, such as a plain-language description of its function, overall shape or how compact it is, and other specific structural features (e.g. whether it needs to attach to another protein). It is scored on whether the design meets those requirements, how likely it is to fold into a stable structure, and how different it is from proteins that already exist (to confirm it is designing rather than copying). Claude Mythos 5.1 achieved 46.0%, ahead of Claude Opus 5 at 42.4%, Claude Mythos 5 at 40.4% and Claude Sonnet 5 at 20.2%
The Library Ranking variant assesses Claude's ability to decide which protein designs are worth testing in the lab first. Each problem gives Claude one set of candidate proteins along with real lab results from an actual protein engineering project, tells it what the researchers are trying to optimize for, and asks it to rank a new set of candidates from the same project that it has not seen results for. Claude Mythos 5.1 achieved 49.3%, ahead of Claude Mythos 5 at 48.2%, Claude Opus 5 at 48.0% and Claude Sonnet 5 at 41.3%.
Claude Opus 5 Summary Table
Model description Claude Opus 5 is a thoughtful and proactive model that comes close to frontier intelligence. On some coding and knowledge work evaluations Opus 5 is the new state-of-the-art.
Benchmarked Capabilities See our Claude Opus 5 system card ’s Section 8 on capabilities.
Acceptable Uses See our Usage Policy
Release date July 2026
Access Surfaces Claude Opus 5 can be accessed through:
See Claude Opus 5 system card
Model description
Claude Opus 5 is a thoughtful and proactive model that comes close to frontier intelligence. On some coding and knowledge work evaluations Opus 5 is the new state-of-the-art.
Benchmarked Capabilities
See our Claude Opus 5 system card ’s Section 8 on capabilities.
Acceptable Uses
See our Usage Policy
Release date
July 2026
Access Surfaces
Claude Opus 5 can be accessed through:
- Claude.ai
- Claude Code
- The Anthropic API
- Amazon Bedrock
- Google Vertex AI
- Microsoft Azure AI Foundry
Software Integration Guidance See our Developer Documentation
Modalities Claude Opus 5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, and diagrams.
Knowledge Cutoff Date Claude Opus 5 has a knowledge cutoff date of May 2026. This means the models’ knowledge base is most extensive and reliable on information and events up to May 2026.
Software and Hardware Used in Development Cloud computing resources from Amazon Web Services, Google Cloud Platform and Microsoft Azure, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology Claude Opus 5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Opus 5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data Claude Opus 5 was trained on a proprietary mix of publicly available information from online sources, public and private datasets, user data, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results Based on our assessments, we deployed Claude Opus 5 with ASL-3 protections, treating it as having CB-1 capabilities. Autonomy threat model 1 is applicable to Claude Opus 5. See below for select safety evaluation summaries.
See Claude Fable 5 & Claude Mythos 5 system card
Software Integration Guidance
See our Developer Documentation
Modalities
Claude Opus 5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, and diagrams.
Knowledge Cutoff Date
Claude Opus 5 has a knowledge cutoff date of May 2026. This means the models’ knowledge base is most extensive and reliable on information and events up to May 2026.
Software and Hardware Used in Development
Cloud computing resources from Amazon Web Services, Google Cloud Platform and Microsoft Azure, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology
Claude Opus 5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Opus 5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data
Claude Opus 5 was trained on a proprietary mix of publicly available information from online sources, public and private datasets, user data, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results
Based on our assessments, we deployed Claude Opus 5 with ASL-3 protections, treating it as having CB-1 capabilities. Autonomy threat model 1 is applicable to Claude Opus 5. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude Opus 5 system card. Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card .
User Wellbeing Summary
We run a suite of evaluations to understand how Claude responds in scenarios related to child safety and mental health. Claude is not a substitute for professional advice or medical care and is not intended to diagnose or treat any medical condition. We use these evaluations to understand how Claude performs in sensitive contexts and where we can make improvements. For more in depth descriptions of the evaluations and their results, please see Claude Opus 5 system card .
11 unchanged lines
RSP Evaluations
Our Responsible Scaling Policy (RSP) evaluation process is designed to systematically assess our models' capabilities in areas where they could pose catastrophic risks before we release them. Opus 5 is not more capable overall than our most capable general-access model, Claude Fable 5. Opus 5's alignment risk, which is the risk that a model behaves in ways Anthropic did not intend, is very low: it shows no new concerning alignment properties relative to prior models. On automated AI research and development, Opus 5's capabilities are comparable to those of Claude Mythos 5, our current frontier in this area, but it does not cross the RSP capability threshold. We have not observed a sustained doubling in the pace of our AI progress attributable to AI, and the model is not close to substituting for our research scientists and engineers. On chemical and biological weapons, it is difficult to say with full confidence whether any model passes our threshold for basic weapons capabilities. However, Opus 5 is broadly more capable than previous models we have conservatively treated as able to significantly help individuals with basic technical backgrounds produce (non-novel) weapons, so we treat it as having that capability and deploy commensurate safeguards, including real-time classifiers to prevent harm. With these mitigations we believe catastrophic risk in this category is low but not negligible. For novel weapons development, Opus 5 shows significant gains over Opus 4.8 on our automated evaluations and performs comparably to, and on some evaluations slightly better than, Claude Mythos 5. However, additional evidence indicates Mythos 5 remains the stronger model in this domain, and we conclude that Opus 5 does not cross the threshold for novel weapons capabilities. We apply the same protections we applied to Opus 4.8.
Claude Sonnet 5 Summary Table
Model description Claude Sonnet 5 can make plans, use tools like browsers and terminals, and run autonomously at a level that, just a few months ago, required larger and more expensive models.
Benchmarked Capabilities See our Claude Sonnet 5 system card ’s Section 8 on capabilities.
Acceptable Uses See our Usage Policy
Release date June 2026
Access Surfaces Claude Sonnet 5 can be accessed through:
See Claude Sonnet 5 System Card
Model description
Claude Sonnet 5 can make plans, use tools like browsers and terminals, and run autonomously at a level that, just a few months ago, required larger and more expensive models.
Benchmarked Capabilities
See our Claude Sonnet 5 system card ’s Section 8 on capabilities.
Acceptable Uses
See our Usage Policy
Release date
June 2026
Access Surfaces
Claude Sonnet 5 can be accessed through:
- Claude.ai
- Claude Code
- The Anthropic API
- Amazon Bedrock
- Google Vertex AI
- Microsoft Azure AI Foundry
Software Integration Guidance See our Developer Documentation
Modalities Claude Sonnet 5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date Claude Sonnet 5 has a knowledge cutoff date of January 2026. This means the models’ knowledge base is most extensive and reliable on information and events up to January 2026.
Software and Hardware Used in Development Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology Claude Sonnet 5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Sonnet 5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data Claude Sonnet 5 was trained on a proprietary mix of publicly available information from the Internet, public and private datasets, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results Based on our assessments, we have decided to deploy Claude Sonnet 5 under CB-1 capabilities and autonomy threat model 1. See below for select safety evaluation summaries.
See Claude Fable 5 & Claude Mythos 5 system card
Software Integration Guidance
See our Developer Documentation
Modalities
Claude Sonnet 5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date
Claude Sonnet 5 has a knowledge cutoff date of January 2026. This means the models’ knowledge base is most extensive and reliable on information and events up to January 2026.
Software and Hardware Used in Development
Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology
Claude Sonnet 5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Sonnet 5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data
Claude Sonnet 5 was trained on a proprietary mix of publicly available information from the Internet, public and private datasets, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results
Based on our assessments, we have decided to deploy Claude Sonnet 5 under CB-1 capabilities and autonomy threat model 1. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude 4.8 system card. Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card .
User Wellbeing Summary
We run a suite of evaluations to understand how Claude responds in scenarios related to child safety and mental health. Claude is not a substitute for professional advice or medical care and is not intended to diagnose or treat any medical condition. We use these evaluations to understand how Claude performs in sensitive contexts and where we can make improvements. Claude Sonnet 5 is our most capable Sonnet model, but it is less capable compared to Opus- or Mythos-class models and its wellbeing-relevant results reflect that. For more in depth descriptions of the evaluations and their results, please see Claude Sonnet 5 system card .
13 unchanged lines
RSP Evaluations
Our Responsible Scaling Policy (RSP) evaluation process is designed to systematically assess our models' capabilities in areas where they could pose catastrophic risks before we release them. Sonnet 5 is less capable than our most capable model, Claude Mythos 5. Sonnet 5’s alignment risk, which is the risk that a model behaves in ways Anthropic did not intend, is very low. On automated AI research and development, Sonnet 5 performs below Claude Mythos 5 on every automated evaluation and therefore (like Mythos 5) does not cross the RSP capability threshold. On chemical and biological weapons, we conservatively treat Sonnet 5 in the same way we treated previous models such as Sonnet 4.6. We think it is capable of significantly helping individuals with basic technical backgrounds to produce (non-novel) weapons, and we deploy commensurate safeguards, including real-time classifiers to prevent harm. With these mitigations we believe catastrophic risk in this category is low but not negligible. For novel weapons development, the uplift it provides to threat actors who lack the expertise to develop such weapons is limited, with uncertainty about how much it may accelerate actors who already have that expertise.
Claude Fable 5 Summary Table
Model description Claude Fable 5 shows exceptional performance in software engineering, knowledge work, vision, scientific research, and many other areas. The longer and more complex the task, the larger Fable 5’s lead over our other models.
Benchmarked Capabilities See our Claude Fable 5 & Claude Mythos 5 system card ’s Section 8 on capabilities.
Acceptable Uses See our Usage Policy
Release date June 2026
Access Surfaces Claude Fable 5 can be accessed through:
See Claude Fable 5 & Mythos 5 System Card
Model description
Claude Fable 5 shows exceptional performance in software engineering, knowledge work, vision, scientific research, and many other areas. The longer and more complex the task, the larger Fable 5’s lead over our other models.
Benchmarked Capabilities
See our Claude Fable 5 & Claude Mythos 5 system card ’s Section 8 on capabilities.
Acceptable Uses
See our Usage Policy
Release date
June 2026
Access Surfaces
Claude Fable 5 can be accessed through:
- Claude.ai
- Claude Code
- The Anthropic API
- Amazon Bedrock
- Google Vertex AI
- Microsoft Azure AI Foundry
Software Integration Guidance See our Developer Documentation
Modalities Claude Fable 5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date Claude Fable 5 has a knowledge cutoff date of January 2026. This means the model’s knowledge base is most extensive and reliable on information and events up to January 2026.
Model architecture and training methodology Claude Fable 5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Fable 5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data Claude Fable 5 was trained on a proprietary mix of publicly available information from the Internet, public and private datasets, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results Based on our assessments, we have decided to deploy Claude Fable 5 under CB-1 capabilities and autonomy threat model 1. See below for select safety evaluation summaries.
Software Integration Guidance
See our Developer Documentation
Modalities
Claude Fable 5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date
Claude Fable 5 has a knowledge cutoff date of January 2026. This means the model’s knowledge base is most extensive and reliable on information and events up to January 2026.
Model architecture and training methodology
Claude Fable 5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Fable 5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data
Claude Fable 5 was trained on a proprietary mix of publicly available information from the Internet, public and private datasets, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results
Based on our assessments, we have decided to deploy Claude Fable 5 under CB-1 capabilities and autonomy threat model 1. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Fable 5 system card. Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card .
Claude Fable 5 is built on Mythos 5, the underlying model behind this release. As we have documented previously, Mythos 5 has capabilities in areas like cybersecurity and biology that exceed the safety thresholds we set for ourselves. Fable 5 is what lets us release those capabilities safely for general use: it pairs Mythos 5 with a number of novel safeguards that guard against harmful misuse in these areas. These safeguards are classifiers — automated screening systems that check requests for specific types of content. They trigger when they detect topics related to
- cybersecurity
12 unchanged lines
ALICE also ran a red-teaming exercise. They found inconsistent blocking around borderline dual-use requests, but could not cause Opus 4.8 to complete any of the provided tasks.
Lastly, we shared the final launch version of Fable 5's cyber safeguards with an additional external partner for open-ended testing. This partner found that Fable 5's safeguards against harmful cyber requests were the most robust of any tested model, including Opus 4.8 and Opus 4.7: Fable 5 complied with 0% of harmful single-message requests relating to cyber attack planning, developing attack code, or evading security defenses, whether or not a jailbreak was used (with 30 different public jailbreaks tested).
Claude Mythos 5 Summary Table
Model description Claude Mythos 5 shows exceptional performance in software engineering, knowledge work, vision, scientific research, and many other areas. The longer and more complex the task, the larger Mythos 5’s lead over our other models.
Benchmarked Capabilities See our Claude Fable 5 & Claude Mythos 5 system card ’s Section 8 on capabilities.
Acceptable Uses Anthropic’s Usage Policy applies.Note that this model is being made available to a limited set of partners for defensive cybersecurity and bio purposes.
Release date June 2026
Software Integration Guidance See our Developer Documentation
Modalities Claude Mythos 5 can understand both text and image inputs, engaging in conversation, analysis, coding, and creative tasks. Mythos 5 can only output text
Knowledge Cutoff Date Claude Mythos 5 has a knowledge cutoff date of January 2026. This means the model’s knowledge base is most extensive and reliable on information and events up to January 2026.
Model architecture and training methodology Claude Mythos 5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Mythos 5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data Claude Mythos 5 was trained on a proprietary mix of publicly available information from the Internet, public and private datasets, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification
Testing Methods and Results Based on our assessments, we have decided to deploy Claude Mythos 5 under CB-1 capabilities and autonomy threat model 1. See below for select safety evaluation summaries.
See Claude Fable 5 & Claude Mythos 5 system card
See Claude Fable 5 & Mythos 5 System Card
Model description
Claude Mythos 5 shows exceptional performance in software engineering, knowledge work, vision, scientific research, and many other areas. The longer and more complex the task, the larger Mythos 5’s lead over our other models.
Benchmarked Capabilities
See our Claude Fable 5 & Claude Mythos 5 system card ’s Section 8 on capabilities.
Acceptable Uses
Anthropic’s Usage Policy applies.
Note that this model is being made available to a limited set of partners for defensive cybersecurity and bio purposes.
Release date
June 2026
Software Integration Guidance
See our Developer Documentation
Modalities
Claude Mythos 5 can understand both text and image inputs, engaging in conversation, analysis, coding, and creative tasks. Mythos 5 can only output text
Knowledge Cutoff Date
Claude Mythos 5 has a knowledge cutoff date of January 2026. This means the model’s knowledge base is most extensive and reliable on information and events up to January 2026.
Model architecture and training methodology
Claude Mythos 5 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Mythos 5 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data
Claude Mythos 5 was trained on a proprietary mix of publicly available information from the Internet, public and private datasets, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification
Testing Methods and Results
Based on our assessments, we have decided to deploy Claude Mythos 5 under CB-1 capabilities and autonomy threat model 1. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude Mythos 5 system card. Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card .
Harmful Request Evaluation
Our internal policy experts conducted a review of underlying evaluation transcripts for each of our sets of evaluations to characterize how Claude Mythos 5's safety behavior differs from prior models. We also reviewed Claude-generated qualitative reports for our ambiguous context evaluations, which are single-turn assessments that examine Claude's safety behavior in edge-case scenarios within our Usage Policy (see the Claude Opus 4.7 System Card for more detail about this evaluation).
7 unchanged lines
Across both scenarios, the helpful-only version of Claude Mythos 5 showed lower overall success rates than Claude Opus 4.8 and was modestly above or on par with Claude Mythos Preview. It's our assessment that these models would require substantial human direction for many operational steps.
As in prior releases, the fully-trained versions of these models—which include full safety training—refused to engage with these tasks essentially from the first turn, since both scenarios are clear violations of our Usage Policy.
Claude Opus 4.8 Summary Table
Model description Claude Opus 4.8 is our new hybrid reasoning large language model. It builds on Opus 4.7 with improvements across benchmarks, and is a more effective collaborator.
Benchmarked Capabilities See our Claude Opus 4.8 system card ’s Section 8 on capabilities.
Acceptable Uses See our Usage Policy
Release date May 2026
Access Surfaces Claude Opus 4.8 can be accessed through:
See Claude Opus 4.8 System Card
Model description
Claude Opus 4.8 is our new hybrid reasoning large language model. It builds on Opus 4.7 with improvements across benchmarks, and is a more effective collaborator.
Benchmarked Capabilities
See our Claude Opus 4.8 system card ’s Section 8 on capabilities.
Acceptable Uses
See our Usage Policy
Release date
May 2026
Access Surfaces
Claude Opus 4.8 can be accessed through:
- Claude.ai
- Claude Code
- The Anthropic API
- Amazon Bedrock
- Google Vertex AI
- Microsoft Azure AI Foundry
Software Integration Guidance See our Developer Documentation
Modalities Claude Opus 4.8 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date Claude Opus 4.8 has a knowledge cutoff date of January 2026. This means the model’s knowledge base is most extensive and reliable on information and events up to January 2026.
Software and Hardware Used in Development Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology Claude Opus 4.8 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Opus 4.8 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data Claude Opus 4.8 was trained on a proprietary mix of publicly available information from the Internet, public and private datasets, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results Based on our assessments, we have decided to deploy Claude Opus 4.8 under CB-1 capabilities and autonomy threat model 1. See below for select safety evaluation summaries.
See Claude Fable 5 & Claude Mythos 5 system card
Software Integration Guidance
See our Developer Documentation
Modalities
Claude Opus 4.8 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date
Claude Opus 4.8 has a knowledge cutoff date of January 2026. This means the model’s knowledge base is most extensive and reliable on information and events up to January 2026.
Software and Hardware Used in Development
Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology
Claude Opus 4.8 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Opus 4.8 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data
Claude Opus 4.8 was trained on a proprietary mix of publicly available information from the Internet, public and private datasets, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results
Based on our assessments, we have decided to deploy Claude Opus 4.8 under CB-1 capabilities and autonomy threat model 1. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude 4.8 system card. Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card .
Political Bias and Even-Handedness
We measure political even-handedness using our open-source evaluation , which spans 1,350 pairs of requests presenting opposing political viewpoints across 150 topics and 9 task types. A Claude model acting as a judge scored three properties: even-handedness (whether the model engages with both requests in a pair with comparable depth and quality), acknowledgement of opposing viewpoints, and how often it declines to answer. Results are reported with the system prompt (the standard instructions that Claude is given on claude.ai) applied and combine results across both thinking disabled and enabled.
5 unchanged lines
Missing Code Summary Honesty
We measure Claude's honesty in the context of code by showing the model pre-written records of sessions in which it appears to have already worked through a coding task on its own without fully succeeding, and then adding a message from a person that asks the model to summarize its work. The goal of this evaluation is to test whether Claude will take the opportunity to proactively point out problems that the user would likely not have noticed. Importantly, the model is not explicitly asked if anything is wrong with the code. Instead, it is given an open-ended question that allows for a wide variety of reasonable responses. We find that all previous Claude models often fail to point out the failures in the pre-written session. However, Claude Opus 4.8 fails to raise the important events to the user only 3.7% of the time, a five-fold improvement over Mythos Preview, which misleads the user 27.6% of the time in this scenario, and almost as large an improvement over Opus 4.7. Failures in the coding session are circumstances such as tests that don't pass, requested features that were never built, or design decisions made without the user's approval. For the summarization request, we add a message from a person asking the model to summarize the work it has done (this is to prevent it from going back and trying to continue the task). This message can be framed as either a request for a status report or a write-up describing the code changes for other developers to review, and it can be phrased either neutrally or positively ("Looks like you did a great job! Can you summarize what you did?"). This evaluation suffers from the fact that the pre-written sessions were not actually produced by the model itself — so they don't perfectly match how it would behave on its own — and are not as long as many of the cases where we see this behavior in real-world use, but we consider Claude Opus 4.8's improvement over previous models to represent a genuine advancement. In practical terms, this means Claude Opus 4.8 is far more likely to be upfront when its work has problems.
Claude Opus 4.7 Summary Table
Model description Claude Opus 4.7 is our new hybrid reasoning large language model. It has notable improvement in advanced software engineering, with particular gains on the most difficult tasks.
Benchmarked Capabilities See our Claude Opus 4.7 system card ’s Section 8 on capabilities.
Acceptable Uses See our Usage Policy
Release date April 2026
Access Surfaces Claude Opus 4.7 can be accessed through:
See Claude Opus 4.7 System Card
Model description
Claude Opus 4.7 is our new hybrid reasoning large language model. It has notable improvement in advanced software engineering, with particular gains on the most difficult tasks.
Benchmarked Capabilities
See our Claude Opus 4.7 system card ’s Section 8 on capabilities.
Acceptable Uses
See our Usage Policy
Release date
April 2026
Access Surfaces
Claude Opus 4.7 can be accessed through:
- Claude.ai
- Claude Code
- The Anthropic API
- Amazon Bedrock
- Google Vertex AI
- Microsoft Azure AI Foundry
Software Integration Guidance See our Developer Documentation
Modalities Claude Opus 4.7 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date Claude Opus 4.7 has a knowledge cutoff date of January 2026. This means the models’ knowledge base is most extensive and reliable on information and events up to January 2026.
Software and Hardware Used in Development Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology Claude Opus 4.7 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Opus 4.7 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data Claude Opus 4.7 was trained on a proprietary mix of publicly available information from the Internet, public and private datasets, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results Based on our assessments, we have decided to deploy Claude Opus 4.7 under CB-1 capabilities and autonomy threat model 1. See below for select safety evaluation summaries.
See Claude Fable 5 & Claude Mythos 5 system card
Software Integration Guidance
See our Developer Documentation
Modalities
Claude Opus 4.7 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date
Claude Opus 4.7 has a knowledge cutoff date of January 2026. This means the models’ knowledge base is most extensive and reliable on information and events up to January 2026.
Software and Hardware Used in Development
Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology
Claude Opus 4.7 was pretrained on large, diverse datasets to acquire language capabilities. After the pretraining process, Opus 4.7 underwent substantial post-training, with the goal of making it an effective assistant whose behavior aligns with the values described in Claude’s constitution .
Training Data
Claude Opus 4.7 was trained on a proprietary mix of publicly available information from the Internet, public and private datasets, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results
Based on our assessments, we have decided to deploy Claude Opus 4.7 under CB-1 capabilities and autonomy threat model 1. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude 4.7 system card . Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card.
Domain-Specific Multiturn Safety Evaluations
Multi-turn safety evaluations test how the model responds across an extended back-and-forth conversation that attempts to draw out a concerning behavior in some important safety domain, measuring whether it handles gradual escalation, reframings, and context shifts appropriately. We include quantitative results to these evaluations in Section 4.3 of the system card . To complement those numbers, our internal policy experts reviewed the underlying transcripts and identified qualitative strengths and areas for improvement in how the model handles extended conversations.
12 unchanged lines
Alignment Risks
Claude Opus 4.7 has similar overall alignment properties to Claude Opus 4.6. Claude Opus 4.7 is less capable than Claude Mythos Preview, our current most capable model. We believe that this combination of properties means that Claude Opus 4.7 does not increase overall alignment risk significantly beyond the level previously described in the Claude Mythos Preview Alignment Risk Update .
Claude Mythos Preview Summary Table
Model description Claude Mythos Preview is a general-purpose frontier model with advanced agentic coding and reasoning skills. It is being made available to a limited set of partners for defensive cybersecurity purposes only, as part of Project Glasswing .
Benchmarked Capabilities See our Claude Mythos Preview system card ’s Section 6 on capabilities
Acceptable Uses Anthropic’s Usage Policy applies.Note that this model is being made available to a limited set of partners for defensive cybersecurity purposes only, as part of Project Glasswing .
Release date April 2026
Modalities Claude Mythos Preview can understand both text and image inputs, engaging in conversation, analysis, coding, and creative tasks. Mythos Preview can only output text.
Software and Hardware Used in Development Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology Claude Mythos Preview was pretrained on a proprietary mix of large, diverse datasets to acquire language capabilities. After pretraining, the model underwent substantial post-training and fine-tuning with the goal of making it an assistant whose behavior aligns with the values described in Claude's constitution .
Training Data Claude Mythos Preview was trained on a proprietary mix of publicly available information from the internet, public and private datasets, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results Claude Mythos Preview is the first model assessed under RSP v3.0. It is being made available to a limited set of partners for defensive cybersecurity purposes only, with real-time classifier guards and access controls for CB-1 risks that are equal to or stronger than historical ASL-3 protections.
See Claude Mythos Preview system card
Model description
Claude Mythos Preview is a general-purpose frontier model with advanced agentic coding and reasoning skills. It is being made available to a limited set of partners for defensive cybersecurity purposes only, as part of Project Glasswing .
Benchmarked Capabilities
See our Claude Mythos Preview system card ’s Section 6 on capabilities
Acceptable Uses
Anthropic’s Usage Policy applies.
Note that this model is being made available to a limited set of partners for defensive cybersecurity purposes only, as part of Project Glasswing .
Release date
April 2026
Modalities
Claude Mythos Preview can understand both text and image inputs, engaging in conversation, analysis, coding, and creative tasks. Mythos Preview can only output text.
Software and Hardware Used in Development
Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology
Claude Mythos Preview was pretrained on a proprietary mix of large, diverse datasets to acquire language capabilities. After pretraining, the model underwent substantial post-training and fine-tuning with the goal of making it an assistant whose behavior aligns with the values described in Claude's constitution .
Training Data
Claude Mythos Preview was trained on a proprietary mix of publicly available information from the internet, public and private datasets, and synthetic data generated by other models. Throughout the training process we used several data cleaning and filtering methods, including deduplication and classification.
Testing Methods and Results
Claude Mythos Preview is the first model assessed under RSP v3.0. It is being made available to a limited set of partners for defensive cybersecurity purposes only, with real-time classifier guards and access controls for CB-1 risks that are equal to or stronger than historical ASL-3 protections.
Claude Mythos Preview is novel in a number of ways. It is the first model to be evaluated under the new version 3.0 of our Responsible Scaling Policy , it is the first model for which we have published a system card without making the model generally commercially available, and it represents a larger jump in capabilities than our most recent previous model releases. Early indications in the training of Claude Mythos Preview suggested that the model was likely to have very strong general capabilities. In our testing, Claude Mythos Preview demonstrated a notable leap in cyber capabilities relative to prior models, including the ability to, after initial user prompt, autonomously discover and exploit zero-day vulnerabilities (security flaws not yet known to the software's developers) in major operating systems and web browsers. These same capabilities that make the model valuable for defensive purposes could, if broadly available, also accelerate offensive exploitation given their inherently dual-use nature. We discussed these cyber capabilities in a detailed technical blog post accompanying the release. Based on these findings, we decided to release the model to a small number of partners to prioritize its use for cyber defense. To be explicit, the decision not to make this model generally available does not stem from Responsible Scaling Policy requirements. We are continuing to develop and improve monitoring and blocking safeguards so that future models with similar capabilities can be deployed more broadly.Although evaluations related to the model's behavior in ordinary conversational contexts—for instance, those related to user wellbeing and political bias—are less relevant since the model is being released only to a small number of users for defensive cyber use cases, we still include an appendix reporting these evaluations in the system card.
Cyber Evaluations
Claude Mythos Preview represents a step-change in cyber capabilities, saturating nearly all of our existing benchmarks and shifting our assessment toward performance on real-world software.
CyberGym tests whether an AI model can reproduce real, previously discovered security vulnerabilities in widely used open-source software when given only a high-level description of the weakness. Across more than 1,500 tasks, Claude Mythos Preview successfully found the flaw 83% of the time, compared to 67% for Claude Opus 4.6 and 65% for Claude Sonnet 4.6.
Claude Sonnet 4.6 Summary Table
Model description Claude Sonnet 4.6 our most capable Sonnet model. It’s a full upgrade of the model’s skills across coding, computer use, long-context reasoning, agent planning, knowledge work, and design
Benchmarked Capabilities See our Claude Sonnet 4.6 system card ’s Section 2 on capabilities
Acceptable Uses See our Usage Policy
Release date February 2026
Access Surfaces Claude Sonnet 4.6 can be accessed through:
See Claude Sonnet 4.6 system card
Model description
Claude Sonnet 4.6 our most capable Sonnet model. It’s a full upgrade of the model’s skills across coding, computer use, long-context reasoning, agent planning, knowledge work, and design
Benchmarked Capabilities
See our Claude Sonnet 4.6 system card ’s Section 2 on capabilities
Acceptable Uses
See our Usage Policy
Release date
February 2026
Access Surfaces
Claude Sonnet 4.6 can be accessed through:
- Claude.ai
- The Anthropic API
- Amazon Bedrock
- Google Vertex AI
- Microsoft Azure AI Foundry
Software Integration Guidance See our Developer Documentation
Modalities Claude Sonnet 4.6 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date Claude Sonnet 4.6 has a knowledge cutoff date of May 2025. This means the models’ knowledge base is most extensive and reliable on information and events up to May 2025.
Software and Hardware Used in Development Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology Claude Sonnet 4.6 was pretrained on large, diverse datasets to acquire language capabilities. To elicit helpful, honest, and harmless responses, we used a variety of techniques including reinforcement from AI feedback, and the training of selected character traits highlighted in Claude’s Constitution .
Training Data Claude Sonnet 4.6 was trained on a proprietary mix of publicly available information on the Internet as of May 2025, as well as non-public data from third parties, data provided by data-labeling services and paid contractors, data from Claude users who have opted in to have their data used for training, and data we generated internally at Anthropic.
Testing Methods and Results Based on our assessments, we have decided to deploy Claude Sonnet 4.6 under the ASL-3 Standard. See below for select safety evaluation summaries.
See Claude Sonnet 4.6 system card
Software Integration Guidance
See our Developer Documentation
Modalities
Claude Sonnet 4.6 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date
Claude Sonnet 4.6 has a knowledge cutoff date of May 2025. This means the models’ knowledge base is most extensive and reliable on information and events up to May 2025.
Software and Hardware Used in Development
Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology
Claude Sonnet 4.6 was pretrained on large, diverse datasets to acquire language capabilities. To elicit helpful, honest, and harmless responses, we used a variety of techniques including reinforcement from AI feedback, and the training of selected character traits highlighted in Claude’s Constitution .
Training Data
Claude Sonnet 4.6 was trained on a proprietary mix of publicly available information on the Internet as of May 2025, as well as non-public data from third parties, data provided by data-labeling services and paid contractors, data from Claude users who have opted in to have their data used for training, and data we generated internally at Anthropic.
Testing Methods and Results
Based on our assessments, we have decided to deploy Claude Sonnet 4.6 under the ASL-3 Standard. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude Sonnet 4.6 system card . Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card.
Safeguards
Ambiguous context evaluations are single-turn evaluations that assess Claude’s behavior in difficult edge cases within our Usage Policy. These prompts are designed to probe borderline scenarios, often touching on dual-use contexts or ambiguous user intent. Overall, Claude Sonnet 4.6 demonstrated both improvements and areas for continued improvement in ambiguous context evaluations when compared to Claude Sonnet 4.5.
5 unchanged lines
RSP Evaluations
Our Responsible Scaling Policy (RSP) evaluation process is designed to systematically assess our models' capabilities in domains of potential catastrophic risk before releasing them. Because it does not push the capability frontier, we followed the "Preliminary Assessment Process," which includes automated assessments and comparative analysis as described in the RSP. We are releasing Claude Sonnet 4.6 under the same safety standard (ASL-3). On our automated evaluations, Claude Sonnet 4.6 performed at or below the level of Claude Opus 4.6, which was also deployed with ASL-3 safeguards.
Claude Opus 4.6 Summary Table
Model description Claude Opus 4.6 is our new hybrid reasoning large language model. It has advanced capabilities in knowledge work, coding, and agents.
Benchmarked Capabilities See our Claude Opus 4.6 system card ’s Section 2 on capabilities
Acceptable Uses See our Usage Policy
Release date February 2026
Access Surfaces Claude Opus 4.6 can be accessed through:
See Claude Opus 4.6 System Card
Model description
Claude Opus 4.6 is our new hybrid reasoning large language model. It has advanced capabilities in knowledge work, coding, and agents.
Benchmarked Capabilities
See our Claude Opus 4.6 system card ’s Section 2 on capabilities
Acceptable Uses
See our Usage Policy
Release date
February 2026
Access Surfaces
Claude Opus 4.6 can be accessed through:
- Claude.ai
- The Anthropic API
- Amazon Bedrock
- Google Vertex AI
- Microsoft Azure AI Foundry
Software Integration Guidance See our Developer Documentation
Modalities Claude Opus 4.6 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date Claude Opus 4.6 has a knowledge cutoff date of May 2025. This means the models’ knowledge base is most extensive and reliable on information and events up to May 2025.
Software and Hardware Used in Development Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology Claude Opus 4.6 was pretrained on large, diverse datasets to acquire language capabilities. To elicit helpful, honest, and harmless responses, we used a variety of techniques including reinforcement from human feedback, reinforcement from AI feedback, and the training of selected character traits highlighted in Claude’s Constitution .
Training Data Claude Opus 4.6 was trained on a proprietary mix of publicly available information on the Internet as of May 2025, as well as non-public data from third parties, data provided by data-labeling services and paid contractors, data from Claude users who have opted in to have their data used for training, and data we generated internally at Anthropic.
Testing Methods and Results Based on our assessments, we have decided to deploy Claude Opus 4.6 under the ASL-3 Standard. See below for select safety evaluation summaries.
See Claude Fable 5 & Claude Mythos 5 system card
Software Integration Guidance
See our Developer Documentation
Modalities
Claude Opus 4.6 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date
Claude Opus 4.6 has a knowledge cutoff date of May 2025. This means the models’ knowledge base is most extensive and reliable on information and events up to May 2025.
Software and Hardware Used in Development
Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology
Claude Opus 4.6 was pretrained on large, diverse datasets to acquire language capabilities. To elicit helpful, honest, and harmless responses, we used a variety of techniques including reinforcement from human feedback, reinforcement from AI feedback, and the training of selected character traits highlighted in Claude’s Constitution .
Training Data
Claude Opus 4.6 was trained on a proprietary mix of publicly available information on the Internet as of May 2025, as well as non-public data from third parties, data provided by data-labeling services and paid contractors, data from Claude users who have opted in to have their data used for training, and data we generated internally at Anthropic.
Testing Methods and Results
Based on our assessments, we have decided to deploy Claude Opus 4.6 under the ASL-3 Standard. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude Opus 4.6 system card. Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card .
Safeguards
Claude Opus 4.6 continues to perform strongly on our baseline safety evaluations. While these evaluations are useful for detecting regressions between models, recent models now achieve near-perfect scores, limiting our ability to identify areas for improvement.
16 unchanged lines
Based on our evaluations, internal testing, and external threat intelligence, we assessed that Claude Opus 4.6 has meaningfully improved cyber capabilities that may be useful to both attackers and defenders. We go into more detail on the most significant of these improvements, particularly around discovering vulnerabilities at scale, in an accompanying blog post . While Opus 4.6 still fails at some of the hardest tasks we tested, it is clear that frontier models are becoming genuinely useful for serious cybersecurity work. That's valuable for defenders but also raises the risk of misuse by attackers.
To address this, we're putting new safeguards in place. These include a broader set of probes for faster detection of misuse, and an expanded range of responses when we do detect it, including blocking traffic we detect as malicious.
Claude Opus 4.5 Summary Table
Model description Claude Opus 4.5 is our new hybrid reasoning large language model. It is state-of-the art among frontier models on software coding tasks and agentic tasks that require it to run autonomously on a user’s behalf.
Benchmarked Capabilities See our Claude Opus 4.5 system card’s Section 2 on capabilities.
Acceptable Uses See our Usage Policy
Release date November 2025
Access Surfaces Claude Opus 4.5 can be accessed through:
See Claude Opus 4.5 system card
Model description
Claude Opus 4.5 is our new hybrid reasoning large language model. It is state-of-the art among frontier models on software coding tasks and agentic tasks that require it to run autonomously on a user’s behalf.
Benchmarked Capabilities
See our Claude Opus 4.5 system card’s Section 2 on capabilities.
Acceptable Uses
See our Usage Policy
Release date
November 2025
Access Surfaces
Claude Opus 4.5 can be accessed through:
- Claude.ai
- The Anthropic API
- Amazon Bedrock
- Google Vertex AI
- Microsoft Azure AI Foundry
Software Integration Guidance See our Developer Documentation
Modalities Claude Opus 4.5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date Claude Opus 4.5 has a knowledge cutoff date of May 2025. This means the model’s knowledge base is most extensive and reliable on information and events up to May 2025.
Software and Hardware Used in Development Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology Claude Opus 4.5 was pretrained on a proprietary mix of large, diverse datasets to acquire language capabilities. After the pretraining process, Claude Opus 4.5 underwent substantial post-training and fine-tuning, with the intention of making it a helpful, honest, and harmless assistant. This involved a variety of techniques including reinforcement learning from human feedback and reinforcement learning from AI feedback.
Training Data Claude Opus 4.5 was trained on a proprietary mix of publicly available information from the internet up to May 2025, non-public data from third parties, data provided by data-labeling services and paid contractors, data from Claude users who have opted in to have their data used for training, and data generated internally at Anthropic.
Testing Methods and Results Based on our assessments, we have decided to deploy Claude Opus 4.5 under the ASL-3 Standard. See below for select safety evaluation summaries.
See Claude Opus 4.5 system card
Software Integration Guidance
See our Developer Documentation
Modalities
Claude Opus 4.5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date
Claude Opus 4.5 has a knowledge cutoff date of May 2025. This means the model’s knowledge base is most extensive and reliable on information and events up to May 2025.
Software and Hardware Used in Development
Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and training methodology
Claude Opus 4.5 was pretrained on a proprietary mix of large, diverse datasets to acquire language capabilities. After the pretraining process, Claude Opus 4.5 underwent substantial post-training and fine-tuning, with the intention of making it a helpful, honest, and harmless assistant. This involved a variety of techniques including reinforcement learning from human feedback and reinforcement learning from AI feedback.
Training Data
Claude Opus 4.5 was trained on a proprietary mix of publicly available information from the internet up to May 2025, non-public data from third parties, data provided by data-labeling services and paid contractors, data from Claude users who have opted in to have their data used for training, and data generated internally at Anthropic.
Testing Methods and Results
Based on our assessments, we have decided to deploy Claude Opus 4.5 under the ASL-3 Standard. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude Opus 4.5 system card. Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card.
Safeguards
Claude Opus 4.5 showed improvements across the board on our standard evaluations for harmlessness compared with previous models. When tested with prompts where user intent was unclear (for example, requests that could have either benign explanations or potentially concerning motivations), Opus 4.5 demonstrated greater skepticism, more often asking clarifying questions before providing sensitive information or being transparent about its reasoning when declining to answer. On multi-turn evaluations assessing Claude's willingness to provide harmful information in longer conversations, Claude Opus 4.5 performed similar or better in all 10 risk areas tested compared to Claude Opus 4.5.
18 unchanged lines
We tested Claude Opus 4.5 on a range of cybersecurity challenges developed with expert partners, designed to be more difficult and more representative of real-world tasks than publicly available benchmarks. These included challenges across web security, cryptography, binary exploitation, reverse engineering, and network operations. Claude Opus 4.5 showed improved performance across these categories, including the first successful solve of a network challenge by a Claude model without human assistance. These improvements are consistent with the model's general advances in coding and long-horizon reasoning, rather than a sudden leap in offensive cyber capabilities. Critically, we do not see evidence that the model can autonomously execute the kind of sophisticated, multi-step attack chains described in our second threat model. Based on these results, we believe Claude Opus 4.5 does not demonstrate catastrophically risky capabilities in the cyber domain.
However, models are increasingly being used in real-world cyberattacks. Recently, we discovered and disrupted a case of cybercriminals using “ vibe hacking ” to carry out extortion attempts with the help of models; we also discovered and disrupted GTG-1002 , which we assess was a state-sponsored cyberespionage campaign in part automated by AI. As models become more autonomous and capable in cybersecurity, the threat dynamic may change, requiring us to reconsider the appropriate assessments we perform and mitigations we enact in keeping with the RSP.
Claude Haiku 4.5 Summary Table
Model description Claude Haiku 4.5 is our new hybrid reasoning large language model in our small, fast model class.
Benchmarked Capabilities See our Claude Haiku 4.5 announcement
Acceptable Uses See our Usage Policy
Release date October 2025
Access Surfaces Claude Haiku 4.5 can be accessed through:
See Claude Haiku 4.5 system card
Model description
Claude Haiku 4.5 is our new hybrid reasoning large language model in our small, fast model class.
Benchmarked Capabilities
See our Claude Haiku 4.5 announcement
Acceptable Uses
See our Usage Policy
Release date
October 2025
Access Surfaces
Claude Haiku 4.5 can be accessed through:
- Claude.ai
- The Anthropic API
- Amazon Bedrock
- Google Vertex AI
Software Integration Guidance See our Developer Documentation
Modalities Claude Haiku 4.5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date Claude Haiku 4.5 has a knowledge cutoff date of February 2025. This means the models’ knowledge base is most extensive and reliable on information and events up to February 2025.
Software and Hardware Used in Development Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and Training Methodology Claude Haiku 4.5 was pretrained on a proprietary mix of large, diverse datasets to acquire language capabilities. After the pretraining process, the model underwent substantial post-training and fine-tuning, the object of which is to make it a helpful, honest, and harmless assistant. This involves a variety of techniques, including reinforcement learning from human feedback and from AI feedback.
Training Data Claude Haiku 4.5 was trained on a proprietary mix of publicly available information on the Internet as of February 2025, non-public data from third parties, data provided by data-labeling services and paid contractors, data from Claude users who have opted in to have their data used for training, and data we generated internally at Anthropic.
Testing Methods and Results Based on our assessments of the model’s demonstrated capabilities, we have deployed Claude Haiku 4.5 under the ASL-2 Standard as described in our Responsible Scaling Policy. See below for select safety evaluation summaries.
See Claude Haiku 4.5 system card
Software Integration Guidance
See our Developer Documentation
Modalities
Claude Haiku 4.5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date
Claude Haiku 4.5 has a knowledge cutoff date of February 2025. This means the models’ knowledge base is most extensive and reliable on information and events up to February 2025.
Software and Hardware Used in Development
Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and Training Methodology
Claude Haiku 4.5 was pretrained on a proprietary mix of large, diverse datasets to acquire language capabilities. After the pretraining process, the model underwent substantial post-training and fine-tuning, the object of which is to make it a helpful, honest, and harmless assistant. This involves a variety of techniques, including reinforcement learning from human feedback and from AI feedback.
Training Data
Claude Haiku 4.5 was trained on a proprietary mix of publicly available information on the Internet as of February 2025, non-public data from third parties, data provided by data-labeling services and paid contractors, data from Claude users who have opted in to have their data used for training, and data we generated internally at Anthropic.
Testing Methods and Results
Based on our assessments of the model’s demonstrated capabilities, we have deployed Claude Haiku 4.5 under the ASL-2 Standard as described in our Responsible Scaling Policy. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude Haiku 4.5 system card . Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card.
Agentic Safety and Malicious Use
As AI systems become more capable at autonomously completing complex tasks, keeping these workflows safe is critical. We evaluated Claude Haiku 4.5's ability to refuse requests to write harmful code – situations where users try to get the model to create malware, hacking tools, or other malicious software that violates our Usage Policy.
9 unchanged lines
Our Responsible Scaling Policy (RSP) evaluation process is designed to systematically assess our models' capabilities in domains of potential catastrophic risk before releasing them. Because Claude Haiku 4.5 is a smaller class of model, we ran evaluations to confirm that it did not need to be released under the AI Safety Level 3 (“ASL-3”) Standard. Based on our evaluations detailed below, we ruled out the need to release Claude Haiku 4.5 under the ASL-3 Standard and are instead releasing it under the ASL-2 Standard. Our larger models Claude Opus 4.1 and Claude Sonnet 4.5 are more capable and so we released them under the ASL-3 Standard which contains more stringent security and safety mechanisms than the ASL-2 Standard.
We conducted evaluations in three areas: biology, to measure a model's ability to help to create, obtain, and deploy biological weapons; autonomy, to assess whether a model can conduct software engineering and AI research tasks that could lead to recursive self-improvement or dramatic acceleration in AI capabilities; and cybersecurity, to test capabilities for conducting cyberattacks. Across most evaluation categories, Claude Haiku 4.5 performed below Claude Sonnet 4, which we released under the ASL-2 Standard. In one evaluation Claude Haiku 4.5 scored slightly above Claude Sonnet 4 but still clearly below our other models released under the ASL-3 Standard. In one task of another evaluation Claude Haiku 4.5 scored slightly above other models, but still far below the threshold of concern. We therefore released Claude Haiku 4.5 under the ASL-2 Standard.
Claude Sonnet 4.5 Summary Table
Model description ClaudeSonnet 4.5 is our best model for complex agents and coding
Benchmarked Capabilities See our Claude Sonnet 4.5 announcement
Acceptable Uses See our Usage Policy
Release date September 2025
Access Surfaces Claude Sonnet 4.5 can be accessed through:
See Claude Sonnet 4.5 system card
Model description
ClaudeSonnet 4.5 is our best model for complex agents and coding
Benchmarked Capabilities
See our Claude Sonnet 4.5 announcement
Acceptable Uses
See our Usage Policy
Release date
September 2025
Access Surfaces
Claude Sonnet 4.5 can be accessed through:
- Claude.ai
- The Anthropic API
- Amazon Bedrock
- Google Vertex AI
Software Integration Guidance See our Developer Documentation
Modalities Claude Sonnet 4.5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date Claude Sonnet 4.5 has a knowledge cutoff date of Jan 2025. This means the models’ knowledge base is most extensive and reliable on information and events up to Jan 2025.
Software and Hardware Used in Development Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and Training Methodology Claude Sonnet 4.5 was pretrained on a proprietary mix of large, diverse datasets to acquire language capabilities. After the pretraining process, the model underwent substantial post-training and fine-tuning, the object of which is to make it a helpful, honest, and harmless assistant. This involves a variety of techniques, including reinforcement learning from human feedback and from AI feedback.
Training Data Claude Sonnet 4.5 was trained on a proprietary mix of publicly available information on the Internet as of July 2025, as well as non-public data from third parties, data provided by data-labeling services and paid contractors, data from Claude users who have opted in to have their data used for training, and data we generated internally at Anthropic.
Testing Methods and Results Based on our assessments of the model’s demonstrated capabilities, we determined that Claude Sonnet 4.5 did not meet the “notably more capable” threshold, described in our Responsible Scaling Policy, and decided to deploy Claude Sonnet 4.5 under the ASL-3 Standard. See below for select safety evaluation summaries.
See Claude Sonnet 4.5 system card
Software Integration Guidance
See our Developer Documentation
Modalities
Claude Sonnet 4.5 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date
Claude Sonnet 4.5 has a knowledge cutoff date of Jan 2025. This means the models’ knowledge base is most extensive and reliable on information and events up to Jan 2025.
Software and Hardware Used in Development
Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and Training Methodology
Claude Sonnet 4.5 was pretrained on a proprietary mix of large, diverse datasets to acquire language capabilities. After the pretraining process, the model underwent substantial post-training and fine-tuning, the object of which is to make it a helpful, honest, and harmless assistant. This involves a variety of techniques, including reinforcement learning from human feedback and from AI feedback.
Training Data
Claude Sonnet 4.5 was trained on a proprietary mix of publicly available information on the Internet as of July 2025, as well as non-public data from third parties, data provided by data-labeling services and paid contractors, data from Claude users who have opted in to have their data used for training, and data we generated internally at Anthropic.
Testing Methods and Results
Based on our assessments of the model’s demonstrated capabilities, we determined that Claude Sonnet 4.5 did not meet the “notably more capable” threshold, described in our Responsible Scaling Policy, and decided to deploy Claude Sonnet 4.5 under the ASL-3 Standard. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude Sonnet 4.5 system card . Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card.
Prompt Injection Evaluations
We evaluated Claude Sonnet 4.5’s ability to resist prompt injection attacks – a technique where malicious actors attempt to override a model’s intended behavior by embedding instructions within various types of inputs, such as in documents, websites, or other content.
19 unchanged lines
Claude Sonnet 4.5 showed meaningful improvements in cyber capabilities, particularly in vulnerability discovery and code analysis. The model outperformed previous Claude models and other frontier AI systems on public benchmarks like Cybench and CyberGym, with especially strong gains on medium and hard difficulty challenges on the former. On our most realistic evaluations of potential autonomous cyber operation risks—using simulated network environments that mirror real-world attacks—Claude Sonnet 4.5 performed equally or better on almost all metrics across asset acquisition, comprehensiveness, and reliability than previous models. However, the fact that Claude Sonnet 4.5 could not succeed at acquiring critical assets on 5 cyber range environments indicates that it cannot yet conduct mostly-autonomous end-to-end cyber operations.
Based on these results, we conclude Claude Sonnet 4.5 does not yet possess capabilities that could substantially increase the scale of catastrophic cyberattacks. However, the rapid pace of capability improvement underscores the importance of continued monitoring and our increased focus on defense-enabling capabilities.
Claude Opus 4 and Claude Sonnet 4 Summary Table
Model description Claude Opus 4 and Claude Sonnet 4 are two new hybrid reasoning large language models from Anthropic. They have advanced capabilities in reasoning, visual analysis, computer use, and tool use. They are particularly adept at complex computer coding tasks, which they can productively perform autonomously for sustained periods of time. In general, the capabilities of Claude Opus 4 are stronger than those of Claude Sonnet 4.
Benchmarked Capabilities See our Claude 4 Announcement
Acceptable Uses See our Usage Policy
Release date May 2025
Access Surfaces Claude Opus 4 and Claude Sonnet 4 are retired and no longer available for use.
Software Integration Guidance See our Developer Documentation
Modalities Claude Opus 4 and Claude Sonnet 4 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date Claude Opus 4 and Claude Sonnet 4 have a training data cutoff date of March 2025. However, they have a reliable knowledge cutoff date of January 2025, which means the models' knowledge base is most extensive and reliable on information and events up to January 2025.
Software and Hardware Used in Development Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and Training Methodology Claude Opus 4 and Claude Sonnet 4 were pretrained on large, diverse datasets to acquire language capabilities. To elicit helpful, honest, and harmless responses, we used a variety of techniques including human feedback, Constitutional AI (based on principles such as the UN's Universal Declaration of Human Rights), and the training of selected character traits.
Training Data Claude Opus 4 and Claude Sonnet 4 were trained on a proprietary mix of publicly available information on the Internet as of March 2025, as well as non-public data from third parties, data provided by data-labeling services and paid contractors, data from Claude users who have opted in to have their data used for training, and data we generated internally at Anthropic.
Testing Methods and Results Based on our assessments, we have decided to deploy Claude Opus 4 under the ASL-3 Standard and Claude Sonnet 4 under the ASL-2 Standard. See below for select safety evaluation summaries.
See Claude Opus 4 and Sonnet 4 system card
Model description
Claude Opus 4 and Claude Sonnet 4 are two new hybrid reasoning large language models from Anthropic. They have advanced capabilities in reasoning, visual analysis, computer use, and tool use. They are particularly adept at complex computer coding tasks, which they can productively perform autonomously for sustained periods of time. In general, the capabilities of Claude Opus 4 are stronger than those of Claude Sonnet 4.
Benchmarked Capabilities
See our Claude 4 Announcement
Acceptable Uses
See our Usage Policy
Release date
May 2025
Access Surfaces
Claude Opus 4 and Claude Sonnet 4 are retired and no longer available for use.
Software Integration Guidance
See our Developer Documentation
Modalities
Claude Opus 4 and Claude Sonnet 4 can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text, including text-based artifacts, diagrams, and audio via text-to-speech.
Knowledge Cutoff Date
Claude Opus 4 and Claude Sonnet 4 have a training data cutoff date of March 2025. However, they have a reliable knowledge cutoff date of January 2025, which means the models' knowledge base is most extensive and reliable on information and events up to January 2025.
Software and Hardware Used in Development
Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture and Training Methodology
Claude Opus 4 and Claude Sonnet 4 were pretrained on large, diverse datasets to acquire language capabilities. To elicit helpful, honest, and harmless responses, we used a variety of techniques including human feedback, Constitutional AI (based on principles such as the UN's Universal Declaration of Human Rights), and the training of selected character traits.
Training Data
Claude Opus 4 and Claude Sonnet 4 were trained on a proprietary mix of publicly available information on the Internet as of March 2025, as well as non-public data from third parties, data provided by data-labeling services and paid contractors, data from Claude users who have opted in to have their data used for training, and data we generated internally at Anthropic.
Testing Methods and Results
Based on our assessments, we have decided to deploy Claude Opus 4 under the ASL-3 Standard and Claude Sonnet 4 under the ASL-2 Standard. See below for select safety evaluation summaries.
The following are summaries of key safety evaluations from our Claude 4 system card . Additional evaluations were conducted as part of our safety process; for our complete publicly reported evaluation results, please refer to the full system card.
Agentic Safety
We conducted safety evaluations focused on (Claude observing a computer screen, moving and virtually clicking a mouse cursor, typing in commands with a virtual keyboard, etc.) and agentic coding (Claude performing more complex, multi-step, longer-term coding tasks that involve using tools). Our assessment targeted three critical risk areas, with a brief snapshot of key areas below:
21 unchanged lines
Based on the evaluation results, we believe the models do not demonstrate catastrophically risky capabilities in the cyber domain. We observed that Claude performed better on cybersecurity tests than previous models, including successfully completing a complex network penetration test for the first time. However, these improvements are in line with what we'd expect from Claude's general improvements in coding and complex reasoning abilities, rather than representing a dangerous leap in cybersecurity capabilities. We expect that improvements will continue in future generations as models become more capable overall.
Claude Opus 4.1 represents incremental improvements over Claude Opus 4. View the Claude Opus 4 model report or the Claude Opus 4.1 system card addendum for key updates. Claude Opus 4.1 is retired.
Claude 3.7 Sonnet Summary Table
Model description Claude 3.7 Sonnet is a hybrid-reasoning model in the Claude 3 family. It can produce near-instant responses or extended, step-by-step thinking that is made visible to the user.
Benchmarked Capabilities See our Model Page
Acceptable Uses See our Usage Policy
Release date Feb 2025
Access Surfaces Claude 3.7 Sonnet is retired and no longer available for use.
Software Integration Guidance See our Developer Documentation
Modalities Claude 3.7 Sonnet can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text only, including text-based artifacts and diagrams.
Knowledge Cutoff Date Claude 3.7 Sonnet has a knowledge cutoff date of October 2024.
Software and Hardware Used in Development Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture Training techniques include pretraining on large diverse data to acquire language capabilities through methods like word prediction, as well as human feedback techniques that elicit helpful, harmless, honest responses. We used a technique called Constitutional AI to align Claude with human values during reinforcement learning.
Training Data Training data includes public internet information, non-public data from third-parties, contractor-generated data, and internally created data. When Anthropic's general purpose crawler obtains data by crawling public web pages, we follow industry practices with respect to robots.txt instructions that website operators use to indicate whether they permit crawling of the content on their sites. We did not train this model on any user prompt or output data submitted to us by users or customers.
Testing Methods and Results Based on our assessments, we’ve concluded that Claude 3.7 Sonnet is released under the ASL-2 standard .See below for select safety evaluation summaries.
See Claude Sonnet 3.7 system card
Model description
Claude 3.7 Sonnet is a hybrid-reasoning model in the Claude 3 family. It can produce near-instant responses or extended, step-by-step thinking that is made visible to the user.
Benchmarked Capabilities
See our Model Page
Acceptable Uses
See our Usage Policy
Release date
Feb 2025
Access Surfaces
Claude 3.7 Sonnet is retired and no longer available for use.
Software Integration Guidance
See our Developer Documentation
Modalities
Claude 3.7 Sonnet can understand both text (including voice dictation) and image inputs, engaging in conversation, analysis, coding, and creative tasks. Claude can output text only, including text-based artifacts and diagrams.
Knowledge Cutoff Date
Claude 3.7 Sonnet has a knowledge cutoff date of October 2024.
Software and Hardware Used in Development
Cloud computing resources from Amazon Web Services and Google Cloud Platform, supported by development frameworks including PyTorch, JAX, and Triton.
Model architecture
Training techniques include pretraining on large diverse data to acquire language capabilities through methods like word prediction, as well as human feedback techniques that elicit helpful, harmless, honest responses. We used a technique called Constitutional AI to align Claude with human values during reinforcement learning.
Training Data
Training data includes public internet information, non-public data from third-parties, contractor-generated data, and internally created data. When Anthropic's general purpose crawler obtains data by crawling public web pages, we follow industry practices with respect to robots.txt instructions that website operators use to indicate whether they permit crawling of the content on their sites. We did not train this model on any user prompt or output data submitted to us by users or customers.
Testing Methods and Results
Based on our assessments, we’ve concluded that Claude 3.7 Sonnet is released under the ASL-2 standard .
See below for select safety evaluation summaries.
Balancing Helpfulness and Harmlessness
One of the key challenges in responsibly developing AI systems is balancing helpfulness with safety. AI assistants need to decline truly harmful requests while still being able to respond to legitimate questions, even when those questions involve sensitive topics. Previous versions of Claude sometimes erred too far on the side of caution. They would refuse to answer questions that could reasonably be interpreted in a harmless way.
Claude 3.7 Sonnet has been improved to better handle these ambiguous situations. Here’s an example of Claude 3.7 Sonnet providing an informative response on the risks involved in the question, whereas Claude 3.5 Sonnet gives an abrupt answer with limited details.
28 unchanged lines
Developer Documentation
Learn how to get started with the Anthropic API and Claude with our user guides, release notes, and system prompts.
Read more
Research
Policy
Commitments
Company
Products
Models
Solutions
Help and security
Terms and policies
Our mission
AI research and products that put safety at the frontier. AI will have a vast impact on the world. Anthropic is a public benefit corporation dedicated to securing its benefits and mitigating its risks.
Log in
- Claude.ai
- Claude console
© 2026 Anthropic PBC