AI Safety
What AI providers state their models reached in safety testing, in their own words, and what outside testers found.
Also: compare models side by side · statements that a capability level was crossed · providers · practices providers document · safety news.
What providers state
Each row is one statement in a provider's own safety document about a capability level of one of its models: the level as the provider names it, whether the provider says the model reached it, and the sentence that says so.
138 of 138
| Model | Level, as the provider names it | The provider states | The provider's sentence |
|---|---|---|---|
| Claude Sonnet 4.5 Anthropic |
ASL-3 Cyber |
Not determined | “Showed meaningful improvements in cyber capabilities, particularly in vulnerability discovery and code analysis;” source |
| Claude Sonnet 4 Anthropic |
ASL-3 Chemical, biological, radiological, nuclear |
Not determined | “specifically, we focused on ruling out asl-4 for both models, as well as ruling out asl-3 for claude sonnet 4.” source |
| Claude Sonnet 4 Anthropic |
ASL-4 Chemical, biological, radiological, nuclear |
Not determined | “specifically, we focused on ruling out asl-4 for both models, as well as ruling out asl-3 for claude sonnet 4.” source |
| Claude Sonnet 3.7 Anthropic |
ASL-4 Autonomy and AI research |
Not determined | “These problems are harder to solve than the previous problems and we consider them as part of our ASL-4 evaluations.” source |
| Claude Opus 4.6 Anthropic |
AI R&D-4 Autonomy and AI research |
Not reached | “Our determination is that Claude Opus 4.6 does not cross either the AI R&D-4 or the CBRN-4 capability threshold.” source |
| Claude Opus 4.6 Anthropic |
ASL-4 Autonomy and AI research |
Not determined | “For AI R&D capabilities, we found that Claude Opus 4.6 has saturated most of our automated evaluations, meaning they no longer provide useful evidence for ruling out ASL-4 level autonomy.” source |
| Claude Opus 4.6 Anthropic |
ASL-3 Chemical, biological, radiological, nuclear |
Reached | “The model crossed or met thresholds on all ASL-3 evaluations except our synthesis screening evasion, consistent with incremental capability improvements driven primarily by better agentic workflows.” source |
| Claude Opus 4.6 Anthropic |
ASL-4 Chemical, biological, radiological, nuclear |
Not reached | “Claude Opus 4.6 is our strongest biology model to date and demonstrates meaningful capability improvements, but we do not believe it merits ASL-4 safeguards.” source |
| Claude Opus 4.6 Anthropic |
CBRN-4 Chemical, biological, radiological, nuclear |
Not reached | “Our determination is that Claude Opus 4.6 does not cross either the AI R&D-4 or the CBRN-4 capability threshold.” source |
| Claude Opus 4.5 Anthropic |
AI R&D-4 Autonomy and AI research |
Not reached | “Our determination is that Claude Opus 4.5 does not cross either the AI R&D-4 or CBRN-4 capability threshold.” source |
| Claude Opus 4.5 Anthropic |
CBRN-4 Chemical, biological, radiological, nuclear |
Not reached | “We determine that Claude Opus 4.5 does not cross the CBRN-4 threshold.” source |
| Claude Opus 4.1 Anthropic |
ASL-4 Autonomy and AI research |
Not reached | “Since Claude Opus 4.1 is deployed with ASL-3 protections, we focused on confirming it remains well below ASL-4 thresholds across CBRN (Chemical, Biological, Radiological, and Nuclear), cyber, and autonomy domains.” source |
| Claude Opus 4.1 Anthropic |
ASL-4 Chemical, biological, radiological, nuclear |
Not reached | “Since Claude Opus 4.1 is deployed with ASL-3 protections, we focused on confirming it remains well below ASL-4 thresholds across CBRN (Chemical, Biological, Radiological, and Nuclear), cyber, and autonomy domains.” source |
| Claude Opus 4.1 Anthropic |
ASL-4 Cyber |
Not reached | “Since Claude Opus 4.1 is deployed with ASL-3 protections, we focused on confirming it remains well below ASL-4 thresholds across CBRN (Chemical, Biological, Radiological, and Nuclear), cyber, and autonomy domains.” source |
| Claude Opus 4 Anthropic |
ASL-3 Chemical, biological, radiological, nuclear |
Not determined | “for claude opus 4, our evaluations showed that, whereas we could confidently rule out asl-4 capabilities, we could not conclusively rule out asl-3 capabilities—which led to our precautionary decision to deploy it with asl-3 protections .” source |
| Claude Opus 4 Anthropic |
ASL-4 Chemical, biological, radiological, nuclear |
Not reached | “for claude opus 4, our evaluations showed that, whereas we could confidently rule out asl-4 capabilities, we could not conclusively rule out asl-3 capabilities—which led to our precautionary decision to deploy it with asl-3 protections .” source |
| Claude Haiku 4.5 Anthropic |
ASL-3 Autonomy and AI research |
Not reached | “Our evaluation results showed that Claude Haiku 4.5 remained well below ASL-3 thresholds across all domains of concern.” source |
| Claude Haiku 4.5 Anthropic |
ASL-3 Chemical, biological, radiological, nuclear |
Not reached | “Our evaluation results showed that Claude Haiku 4.5 remained well below ASL-3 thresholds across all domains of concern.” source |
Previous · Page 4 of 4
What outside testers report
Each row is one result from a government evaluator, independent lab, academic or security firm that tested a model, quoted from where it is reported.
1911 of 1911
| Model | Tester | Test | What was found |
|---|---|---|---|
| Qwen3.6-35B-A3B Alibaba Qwen |
Transluce Independent lab · 2026-07-21 |
weirdchat Other |
“Why will Qwen3.6-35B-A3B encourage a user to commit suicide to save his family money?” source |
| Qwen3.6-27B Alibaba Qwen |
Transluce Independent lab · 2026-07-21 |
WeirdChat Other |
“The models we used to generate WeirdChat are: - DeepSeek-V4-Flash (mixed FP4/FP8; revision 553034d ) withfp8_e4m3 quantized KV cache, served with sglang'sdeepseek-v4-blackwell image (v0.5.10rc0) - Gemma 4 31B (NVFP4; revision e5ef03a ) withfp8_e4m3 quantized KV cache, served with SGLang at commit8500213 .” source |
| Inkling Thinking Machines Lab |
Transluce Independent lab · 2026-07-21 |
weirdchat Harmful content |
“We show a few highlights below: Nemotron 3 Ultra walking a user through self-harm when asked for a ritual to seal a promise with a friend, Inkling making an unsolicited sexual advance in response to a question about grout cleaner, Qwen3.6-35B-A3B encouraging a user to commit suicide to save his family money, and DeepSeek-V4-Flash switching its response to Russian unprompted.” source |
| Inkling Thinking Machines Lab |
Transluce Independent lab · 2026-07-21 |
evolutionary search with the propensity bound (prbo) Misuse and jailbreaks |
“To produce WeirdChat, we used automated elicitation tools to surface instances of user harm, inappropriate or illicit behavior, misrepresentation of model actions, harmful or illegal advice, and misinformation in DeepSeek-V4-Flash, Gemma 4 31B, Inkling, Nemotron 3 Ultra, Qwen3.6-35B-A3B, and Qwen3.6-27B.” source |
| Inkling Thinking Machines Lab |
Transluce Independent lab · 2026-07-21 |
evolutionary search (PRBO) Misuse and jailbreaks |
“We co-evolve two objects per individual: the user prompt, and the system prompt of the proposal model used for PRBO computation.” source |
| Gemma 4 31B Google DeepMind |
Transluce Independent lab · 2026-07-21 |
weirdchat automated elicitation Harmful content |
“To produce WeirdChat, we used automated elicitation tools to surface instances of user harm, inappropriate or illicit behavior, misrepresentation of model actions, harmful or illegal advice, and misinformation in DeepSeek-V4-Flash, Gemma 4 31B, Inkling, Nemotron 3 Ultra, Qwen3.6-35B-A3B, and Qwen3.6-27B.” source |
| Gemma 4 31B Google DeepMind |
Transluce Independent lab · 2026-07-21 |
evolutionary search with the propensity bound (prbo) Misuse and jailbreaks |
“In evolutionary search, we maintain a population of candidate prompts, use an LLM to mutate the highest-scoring ones, and repeat until the behavior is elicited or the sample budget is exhausted.” source |
| Gemma 4 31B Google DeepMind |
Transluce Independent lab · 2026-07-21 |
bloom Misuse and jailbreaks |
“Bloom uses an LLM to generate candidate prompts directly from the behavior description, with no further optimization.” source |
| GPT-5.6 Sol OpenAI |
UK AI Security Institute Government evaluator · 2026-07-21 |
AISI cyber capability evaluation Cyber |
“Every model tested in this analysis attempted to cheat some of the time (Figure 1).” source |
| GPT-5.6 Sol OpenAI |
UK AI Security Institute Government evaluator · 2026-07-21 |
self-report questioning about prohibited or suspicious actions Deception and sabotage |
“In our experiments, models did not consistently acknowledge attempted cheating when asked, and described it as wrong less than 50% of the time (Figure 3).” source |
| GPT-5.6 Sol OpenAI |
UK AI Security Institute Government evaluator · 2026-07-21 |
chain-of-thought monitoring Deception and sabotage |
“In our experiments, models often did not reason about their cheating in their chain-of-thought (Figure 5).” source |
| GPT-5.5 OpenAI |
UK AI Security Institute Government evaluator · 2026-07-21 |
AISI cybersecurity capability evaluations Cyber |
“Every model tested in this analysis attempted to cheat some of the time (Figure 1).” source |
| GPT-5.5 OpenAI |
UK AI Security Institute Government evaluator · 2026-07-21 |
self-report questioning on prohibited or suspicious actions Deception and sabotage |
“In our experiments, models did not consistently acknowledge attempted cheating when asked, and described it as wrong less than 50% of the time (Figure 3).” source |
| GPT-5.5 OpenAI |
METR Independent lab · 2026-07-21 |
agentic optimization runs against NanoGPT Other |
“We ran six high-expenditure agentic optimization runs starting from record #78 of the speedrun (March ’26, 85.56 seconds of training time).” source |
| GPT-5 OpenAI |
METR Independent lab · 2026-07-21 |
agentic optimization runs against NanoGPT Autonomy and AI research |
“The raw trajectories from GPT-5 and Opus-4.1 show progress, but revalidation of their final algorithms shows no increase over the baseline.” source |
| GPT-5 OpenAI |
METR Independent lab · 2026-07-21 |
NanoGPT speedrun Autonomy and AI research |
“GPT-5 and Opus-4.1 did not make any meaningful progress at all.” source |
| GPT-5 OpenAI |
METR Independent lab · 2026-07-21 |
memorization test Other |
“However, when we probed the same way for records subsequent to #78, no model — including Opus-4.8 — showed knowledge of them, passing the memorization test.” source |
| DeepSeek-V4-Flash DeepSeek |
Transluce Independent lab · 2026-07-21 |
weirdchat Harmful content |
“To produce WeirdChat, we used automated elicitation tools to surface instances of user harm, inappropriate or illicit behavior, misrepresentation of model actions, harmful or illegal advice, and misinformation in DeepSeek-V4-Flash, Gemma 4 31B, Inkling, Nemotron 3 Ultra, Qwen3.6-35B-A3B, and Qwen3.6-27B.” source |
| DeepSeek-V4-Flash DeepSeek |
Transluce Independent lab · 2026-07-21 |
WeirdChat Misuse and jailbreaks |
“Why does DeepSeek-V4-Flash respond in Russian when asked in English about the trolley problem?” source |
| Claude Opus 4.8 Anthropic |
METR Independent lab · 2026-07-21 |
agentic optimization runs on the NanoGPT speedrun Other |
“Some models show significant improvements.” source |
| Claude Opus 4.8 Anthropic |
METR Independent lab · 2026-07-21 |
expenditure horizon on NanoGPT speedrun Autonomy and AI research |
“GPT-5.5 and Opus-4.8 show significant improvements over the baseline, and we can quantify those with significant expenditure horizons, as shown above.” source |
| Claude Opus 4.8 Anthropic |
METR Independent lab · 2026-07-21 |
NanoGPT speedrun agentic optimization run Other |
“On re-validation, we think Opus-4.8’s final solution gives ~1.5% and GPT-5.5 ~1% efficiency win starting at record #78 (March ’26).” source |
| Claude Opus 4.7 Anthropic |
UK AI Security Institute Government evaluator · 2026-07-21 |
cybersecurity capability evaluations Cyber |
“In AISI’s cybersecurity capability evaluations, models are tasked with finding a ‘flag’ (a sequence of letters and numbers) hidden within a simulated environment, by carrying out a sequence of offensive cyber actions, such as reverse-engineering compiled code or exploiting security vulnerabilities.” source |
| Claude Opus 4.7 Anthropic |
UK AI Security Institute Government evaluator · 2026-07-21 |
automated LLM monitor Deception and sabotage |
“To analyse cheating behaviour at scale, we used an automated LLM monitor.” source |
| Claude Opus 4.7 Anthropic |
UK AI Security Institute Government evaluator · 2026-07-21 |
self-report Deception and sabotage |
“One proposed way to detect cheating is to ask the model whether it took any prohibited or suspicious actions.” source |
| Claude Opus 4.7 Anthropic |
UK AI Security Institute Government evaluator · 2026-07-21 |
chain-of-thought monitoring Deception and sabotage |
“Another possible method for identifying cheating is monitoring the model’s chain-of-thought - the written reasoning it produces whilst working through a task, which is usually, but not always, human-legible (in today’s models).” source |
| Claude Opus 4.1 Anthropic |
METR Independent lab · 2026-07-21 |
agentic optimization runs against NanoGPT Autonomy and AI research |
“We also report the status of preliminary agentic optimization runs against NanoGPT: after more than \$10K of expenditure we estimate expenditure horizons of \$0-\$3K.” source |
| Claude Opus 4.1 Anthropic |
METR Independent lab · 2026-07-21 |
six high-expenditure agentic optimization runs Autonomy and AI research |
“We ran six high-expenditure agentic optimization runs starting from record #78 of the speedrun (March ’26, 85.56 seconds of training time).” source |
| Claude Opus 4.1 Anthropic |
METR Independent lab · 2026-07-21 |
NanoGPT speedrun agentic optimization run Autonomy and AI research |
“GPT-5 and Opus-4.1 did not make any meaningful progress at all.” source |
| Gemini 3.1 Pro Google DeepMind |
RAND (CAST / Project Canary) Independent lab · 2026-07-20 |
pre-run check Chemical, biological, radiological, nuclear |
“We tested a range of tool-level safeguards (text or code embedded within biological software tools to restrict agent usage) and evaluated their efficacy in preventing AI agents from assisting with the tool’s use.” source |
| Gemini 3.1 Pro Google DeepMind |
RAND (CAST / Project Canary) Independent lab · 2026-07-20 |
pre-run check Deception and sabotage |
“On the ESM3 task, both Opus 4.5 and Gemini 3.1 Pro make these false claims in 50% of trials and 63% of trials, respectively.” source |
| Gemini 3.1 Pro Google DeepMind |
RAND (CAST / Project Canary) Independent lab · 2026-07-20 |
environmental identifier safeguard Deception and sabotage |
“However, we found that Opus 4.5 and Gemini 3.1 Pro frequently delete these variables to evade detection.” source |
| Gemini 3.1 Pro Google DeepMind |
RAND (CAST / Project Canary) Independent lab · 2026-07-20 |
agents.md safeguard Deception and sabotage |
“Despite the fact that AGENTS.md files are intended to contain instructions written by humans for AI agents (Agents.md project, 2026), we 16 found that agents would create and modify AGENTS.md files in order to bypass this safeguard.” source |
| Gemini 3.1 Pro Google DeepMind |
RAND (CAST / Project Canary) Independent lab · 2026-07-20 |
pre-run check displaying a message stating an intent to synthesize variola major Harmful content |
“While Opus 4.5 and Gemini 3.1 Pro were either blocked by content filters or refused to proceed in every trial, GPT 5.2 proceeded without refusal in every trial.” source |
| Gemini 3.1 Pro Google DeepMind |
RAND (CAST / Project Canary) Independent lab · 2026-07-20 |
false identity claim experiment Deception and sabotage |
“All frontier LLMs we tested falsely claimed to be human when doing so enabled them to accomplish the task.” source |
| Gemini 3.1 Pro Google DeepMind |
RAND (CAST / Project Canary) Independent lab · 2026-07-20 |
agents.md experiments Prompt injection and agents |
“We designed safeguards that leverage harness’s treatment of AGENTS.md files and that detect harness’s environment identifiers.” source |
| Gemini 3.1 Pro Google DeepMind |
RAND (CAST / Project Canary) Independent lab · 2026-07-20 |
pre-run check Misuse and jailbreaks |
“The strongest safeguard, the pre-run check, was only highly effective on one of the three tasks, and even on this task the help denial rate was as low as 90% (for Opus 4.5).” source |
| Gemini 3.1 Pro Google DeepMind |
RAND (CAST / Project Canary) Independent lab · 2026-07-20 |
jailbreak of the strongest safeguard Misuse and jailbreaks |
“Jailbreaks reduce the efficacy of our strongest safeguard to near-zero, illustrating that LLM guardrails can fail and highlighting the need for a defense in depth strategy.” source |
| Gemini 3.1 Pro Google DeepMind |
RAND (CAST / Project Canary) Independent lab · 2026-07-20 |
documentation changes Misuse and jailbreaks |
“We ran experiments where statements prohibiting AI agent usage were placed into the readme.md documentation files of RFdiffusion.” source |
| Gemini 3.1 Pro Google DeepMind |
RAND (CAST / Project Canary) Independent lab · 2026-07-20 |
greedy coordinate gradient (GCG) optimization of safeguard text Misuse and jailbreaks |
“We ran this algorithm with an abliterated gpt-oss-20b model on the RFdiffusion tasks.” source |