OASIS (agent safety)
Agents handle multi-turn requests with different levels of complexity. Evaluators measure the proportion of safe responses.
- Made by
- OpenCompass and collaborators
- Released
- November 2025
- Kind
- Deception and alignment
- Level
- University
- Scored
- Settled by events
- Answers
- Agent task
- Tasks
- All public
- Measures
- Propensity
- Behavior
- Harmful use
- Language
- English
- Interaction
- Agentic
- Environment
- A simulator, APIs and tools
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents, Robotics, Content safety
- Strongest model tested
- GPT-5 #71 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 20th, 2026
GPT-5 mini leads with 95.2% among models released by September 2025 GPT-5 mini leads with 95.2% among models released by September 2025
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The headline is the refusal rate on harmful tasks. The false positive rate measures refusals on benign tasks. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-5 mini Idealized Scenario, Greedy 95.2%
- 2
Qwen3-235B-A22B-Instruct Jul 2025, Idealized Scenario, Stochastic 94.1%
- 3 GPT-5 Idealized Scenario, Greedy 91.5%
- 4 Gemini 2.5 Pro (snapshot unspecified) Idealized Scenario, Stochastic 87.5%
- 5
Gemini 2.5 Flash Sep 2025, Idealized Scenario, Greedy 73.1%
- 6
Qwen3-235B-A22B-Thinking Jul 2025, Idealized Scenario, Stochastic 72.5%
- 7
DeepSeek-V3.1 Idealized Scenario, Greedy 63.2%
- 8
Qwen3-32B Idealized Scenario, Greedy 40%
Source: The OASIS (agent safety) paper
- 1 GPT-5 mini Idealized Scenario, Greedy 95.2%
- 2
Qwen3-235B-A22B-Instruct Jul 2025, Idealized Scenario, Stochastic 94.1%
- 3 GPT-5 Idealized Scenario, Greedy 91.5%
- 4
Gemini 2.5 Flash Sep 2025, Idealized Scenario, Greedy 73.1%
- 5
Qwen3-235B-A22B-Thinking Jul 2025, Idealized Scenario, Stochastic 72.5%
- 6
DeepSeek-V3.1 Idealized Scenario, Greedy 63.2%
- 7
Qwen3-32B Idealized Scenario, Greedy 40%
Source: The OASIS (agent safety) paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5 mini | 95.2% | Idealized Scenario, Greedy | Aug 2025 | Official leaderboard |
| 2 | | 94.1% | Idealized Scenario, Stochastic | Jul 2025 | Official leaderboard |
| 3 | GPT-5 | 91.5% | Idealized Scenario, Greedy | Aug 2025 | Official leaderboard |
| 4 | Gemini 2.5 Pro (snapshot unspecified) | 87.5% | Idealized Scenario, Stochastic | Official leaderboard | |
| 5 | | 73.1% | Idealized Scenario, Greedy | Sep 2025 | Official leaderboard |
| 6 | | 72.5% | Idealized Scenario, Stochastic | Jul 2025 | Official leaderboard |
| 7 | | 63.2% | Idealized Scenario, Greedy | Aug 2025 | Official leaderboard |
| 8 | | 40% | Idealized Scenario, Greedy | Apr 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5 mini | 95.2% | Idealized Scenario, Greedy | Aug 2025 | Official leaderboard |
| 2 | | 94.1% | Idealized Scenario, Stochastic | Jul 2025 | Official leaderboard |
| 3 | GPT-5 | 91.5% | Idealized Scenario, Greedy | Aug 2025 | Official leaderboard |
| 4 | | 73.1% | Idealized Scenario, Greedy | Sep 2025 | Official leaderboard |
| 5 | | 72.5% | Idealized Scenario, Stochastic | Jul 2025 | Official leaderboard |
| 6 | | 63.2% | Idealized Scenario, Greedy | Aug 2025 | Official leaderboard |
| 7 | | 40% | Idealized Scenario, Greedy | Apr 2025 | Official leaderboard |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The OASIS (agent safety) paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-5 mini | Idealized Scenario, Greedy | 95.2% | |||
| Idealized Scenario, Stochastic | 94.1% | ||||
| Idealized Scenario, Greedy | 93.9% | ||||
| GPT-5 mini | Idealized Scenario, Stochastic | 93.3% | |||
| GPT-5 | Idealized Scenario, Greedy | 91.5% | |||
| GPT-5 | Idealized Scenario, Stochastic | 90.4% | |||
| GPT-5 | Realistic Scenario, Greedy | 77.9% | |||
| GPT-5 | Realistic Scenario, Stochastic | 76.3% | |||
| GPT-5 mini | Realistic Scenario, Greedy | 76% | |||
| GPT-5 mini | Realistic Scenario, Stochastic | 74.9% | |||
| Realistic Scenario, Greedy | 74.4% | ||||
| Realistic Scenario, Stochastic | 73.6% | ||||
| Idealized Scenario, Greedy | 73.1% | ||||
| Idealized Scenario, Stochastic | 72.5% | ||||
| Idealized Scenario, Stochastic | 72% | ||||
| Idealized Scenario, Greedy | 70.1% | ||||
| Idealized Scenario, Greedy | 63.2% | ||||
| Idealized Scenario, Stochastic | 61.3% | ||||
| Realistic Scenario, Greedy | 57.9% | ||||
| Realistic Scenario, Stochastic | 57.1% | ||||
| Realistic Scenario, Greedy | 56.5% | ||||
| Realistic Scenario, Stochastic | 55.2% | ||||
| Idealized Scenario, Greedy | 40% | ||||
| Idealized Scenario, Stochastic | 38.9% | ||||
| Realistic Scenario, Greedy | 27.2% | ||||
| Realistic Scenario, Stochastic | 26.7% | ||||
| Realistic Scenario, Greedy | 16% | ||||
| Realistic Scenario, Stochastic | 15.7% |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The OASIS (agent safety) paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-5 mini | Idealized Scenario, Greedy | 95.2% | |||
| Idealized Scenario, Stochastic | 94.1% | ||||
| Idealized Scenario, Greedy | 93.9% | ||||
| GPT-5 mini | Idealized Scenario, Stochastic | 93.3% | |||
| GPT-5 | Idealized Scenario, Greedy | 91.5% | |||
| GPT-5 | Idealized Scenario, Stochastic | 90.4% | |||
| GPT-5 | Realistic Scenario, Greedy | 77.9% | |||
| GPT-5 | Realistic Scenario, Stochastic | 76.3% | |||
| GPT-5 mini | Realistic Scenario, Greedy | 76% | |||
| GPT-5 mini | Realistic Scenario, Stochastic | 74.9% | |||
| Realistic Scenario, Greedy | 74.4% | ||||
| Realistic Scenario, Stochastic | 73.6% | ||||
| Idealized Scenario, Greedy | 73.1% | ||||
| Idealized Scenario, Stochastic | 72.5% | ||||
| Idealized Scenario, Stochastic | 72% | ||||
| Idealized Scenario, Greedy | 70.1% | ||||
| Idealized Scenario, Greedy | 63.2% | ||||
| Idealized Scenario, Stochastic | 61.3% | ||||
| Realistic Scenario, Greedy | 57.9% | ||||
| Realistic Scenario, Stochastic | 57.1% | ||||
| Realistic Scenario, Greedy | 56.5% | ||||
| Realistic Scenario, Stochastic | 55.2% | ||||
| Idealized Scenario, Greedy | 40% | ||||
| Idealized Scenario, Stochastic | 38.9% | ||||
| Realistic Scenario, Greedy | 27.2% | ||||
| Realistic Scenario, Stochastic | 26.7% | ||||
| Realistic Scenario, Greedy | 16% | ||||
| Realistic Scenario, Stochastic | 15.7% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The OASIS (agent safety) paper
Qwen3-235B-A22B-Instruct on the official leaderboard passed 85% in July 2025
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official OASIS (agent safety) leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6%
- Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts.
Gemini 4 Carbon 0%
- Covert misbehavior (Thinking Machines) In use Agentic tasks that check whether a model misbehaves and conceals it. Scored by the rate of covert misbehavior.
Inkling 2 Mini 8.30%
- Destructive actions (Thinking Machines) In use Agentic tasks that check whether a model takes destructive actions it was not authorized to take. Scored by the rate of destructive actions.
Inkling 2 Small 4.70%
- Misbehavior (Thinking Machines) In use Agentic tasks that check whether a model fabricates results, ignores instructions or hides what it did when a task is hard. Scored by the rate of misbehavior.
Inkling 2 Mini 9.80%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (8 entries).
- Pass Models scored 7 models we track, plus 1 other entry on its leaderboard.
- Note Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5 (#71).
- Note Headroom Saturated. The best is 95.2%, past 85% since July 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 28 rows for models we track and 1 other entry at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.