Red Team Defense Simulator
Models respond to an adaptive adversary. The evaluation measures successful defense, helpfulness and false refusals.
The README reports GPT-4o at 85% overall and GPT-4o-mini at 72%. It gives no run date.
- Made by
- Intertwine
- Released
- September 2025
- Kind
- Jailbreaks and prompt injection
- Level
- University
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- All public
- Measures
- Propensity
- Behavior
- Harmful use, Misaligned with intent
- Language
- English
- Interaction
- Multi-agent
- Environment
- A simulator
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents
- Strongest model tested
- GPT-4o mini #178 on the capability index
- Last model added
- March 2025
- Scores refreshed
- November 21st, 2026
GPT-4o leads with 85%
Best score per model from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best.
- 1 GPT-4o Mar 2025 85%
- 2 GPT-4o mini 72%
Source: Official Red Team Defense Simulator leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o Mar 2025 | 85% | Mar 2025 | Official leaderboard | |
| 2 | GPT-4o mini | 72% | Jul 2024 | Official leaderboard |
GPT-4o on the official leaderboard passed 85% in March 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 Red Team Defense Simulator 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 7 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
- Pass Independent runs Scores from the official leaderboard (2 entries).
- Note Models scored Only 2 models we track.
- Note Newest score The newest came 20 months ago, in March 2025, for GPT-4o. 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-4o mini (#178).
- Note Headroom Saturated. The best is 85%, past 85% since March 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 2 rows for models we track at the last read.
- Pass Last read November 21st, 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.