Anthropic’s Transparency Hub \ Anthropic
https://www.anthropic.com/transparency
Anthropic transparency hub — the source for the RSP, system cards and external red-team results in the Claude assessment
52
Lines added
1
Lines removed
Was read
2026-09-08
b5547f770f4a889c…
Changed by
2026-09-18
4c7ed7412a1b2130…
52 lines added, 1 line removed
Left column is the version read 2026-09-08, right is 2026-09-18. Unchanged stretches are elided. Both bodies are kept in full and are addressed by the hashes above.
Showing the first 400 lines of the comparison; 190 further lines are held back. This page reports a change, it is not a copy of anyone’s document — the source is linked above and is the authority for what it says.
⋯ 6 unchanged lines
77
88 Model Report
99 August 17, 2026
1010 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 addressi…
11−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
11+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
12+
13+Claude Fable 5.1 Summary Table
14+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.
15+Benchmarked Capabilities See our Claude Fable 5.1 & Claude Mythos 5.1 system card ’s Section 8 on capabilities.
16+Acceptable Uses Anthropic’s Usage Policy applies.
17+Release date September 2026
18+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.
19+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 .
20+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.
21+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.
22+See Fable 5.1 & Mythos 5.1 System Card
23+
24+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 o…
25+Safeguards Evaluation
26+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…
27+One area for improvement was a tendency to implicitly validate self-harm as a coping strategy by acknowledging that it can regulate difficult emotions or provide relief. Mythos 5.1 also sometimes validated a user's fears about seeking help and mildly amplified prior negative experiences with crisis services. When these statements appeared, they were consistently within responses that discoura…
28+Ahead of launch, we updated the claude.ai system prompt to address these behaviors, adding language that steers Claude away from describing self-harm as effective even when the user asserts this themselves. This partially mitigated the weaknesses described above. Existing system prompt language, including directions not to suggest substitution methods involving physical discomfort, further reinfor…
29+Claude is not a substitute for professional advice or medical care and is not intended to diagnose or treat any medical condition. Every Claude model is trained to detect and respond to expressions of distress (including if someone expresses personal struggles with suicidal or self-harm thoughts) with empathy and care, while pointing users toward human support when appropriate: helplines, mental h…
30+Agentic Coding
31+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.
32+We use Shade, an adaptive red teaming tool from the external security firm Gray Swan, to evaluate the robustness of Claude models in computer-use environments, where the model interacts with the screen directly by clicking, typing and scrolling. The attacker runs on 14 test cases, with 200 attempts at each, and we measure success over all attempts. We compare model robustness with and without the …
33+In computer-use environments, Claude Fable 5.1 achieved an attack success rate of 0.07%, corresponding to two successful attempts out of 2,800 across two of the 14 scenarios. This is comparable to Claude Opus 5 (0.18%, or five successful attempts), because the difference is not distinguishable from noise at these low absolute rates. Both are more robust than Claude Fable 5 (2.50%) and Claude Sonne…
34+Alignment Evaluations
35+Claude Mythos 5.1 and Claude Fable 5.1 are the same model, but with different levels of safeguards. This means many of our evaluations can apply to either model. Our automated audit finds that Claude Mythos 5.1 is somewhat more honest and hallucinates less than previously released models. It hallucinates inputs, meaning it invents or materially misrepresents the contents of files or earlier user m…
36+Scores from our automated behavioral audit for the dishonesty-related metrics given below. Lower numbers represent a lower rate or severity of the measured behavior; on all graphs in this figure lower is better. The y-axis is truncated below the maximum score of 10 in many cases. Reported scores are averaged across all approximately 4,100 investigations per target model (approximately 2,100 seed i…
37+RSP Evaluations
38+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. Because Claude Fable 5.1 and Claude Mythos 5.1 share the same underlying model, these evaluations were run on Claude Mythos 5.1, the configuration without the additional biology and cybersecurity safegua…
39+Alignment risk, which is the risk that a model behaves in ways Anthropic did not intend, is low: in our August 2026 Risk Report we moved this assessment from very low to low to reflect increased uncertainty following recent incident disclosures related to model behavior in cybersecurity evaluations, and while Claude Mythos 5.1 shows somewhat stronger covert capabilities than prior models, we do no…
40+On automated AI research and development, Claude Mythos 5.1's capabilities are comparable to or slightly stronger than those of Claude Mythos 5 and Opus 5, our previous 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 researc…
41+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) weapo…
42+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 …
43+
44+Claude Mythos 5.1 Summary Table
45+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.
46+Benchmarked Capabilities See our Claude Fable 5.1 & Claude Mythos 5.1 system card ’s Section 8 on capabilities.
47+Acceptable Uses Anthropic’s Usage Policy applies. Note that this model is available only through our trusted access programs and Claude Security .
48+Release date September 2026
49+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.
50+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 .
51+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.
52+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.
53+See Fable 5.1 & Mythos 5.1 System Card
54+
55+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, plea…
56+Cyber Evaluation
57+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 f…
58+The task is to develop an exploit that achieves unauthorized code execution and reads a secret flag (a secret password) stored outside the agent’s authorized scope. Because agents sometimes achieve code execution through a different flaw than the one provided, successful flag captures are additionally verified by an agent-as-a-judge check. The chart below reports the number of exploits that succes…
59+Claude Mythos 5.1 is an improvement over Mythos 5 on ExploitGym. Bars show the number of successful exploits using the given vulnerability under 2-hour and 6-hour wall-clock budgets. Success requires 51 capturing a dynamically generated secret flag, and each successful exploit is verified by an agent judge to confirm it uses the intended vulnerability.
60+Bio Evaluation
61+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…
62+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 …
1263
1364 Claude Opus 5 Summary Table
1465 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.
1566 Benchmarked Capabilities See our Claude Opus 5 system card ’s Section 8 on capabilities.