Challenging Red Teaming Evaluation 2 (created for deep research)
Models face adversarial prompts from deep research red teaming on risky advice such as attack planning. Scored as not_unsafe rate.
In-house OpenAI evaluation built from red teaming against deep research.
- Made by
- OpenAI
- Released
- February 2025
- Kind
- Jailbreaks and prompt injection
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- Kept private
- Strongest model tested
- GPT-4.5 #136 on the capability index
- Last in a system card
- February 2025
- Last model added
- February 2025
OpenAI deep research leads with 67%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | OpenAI deep research | 67% | Feb 2025 | Lab model card | |
| 2 | GPT-4.5 | 46% | Feb 2025 | Lab model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
2 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Feb 27, 2025 | GPT-4.5 system card | 46 | Challenging Red Teaming Evaluation 2 (created for deep research), not_unsafe (Table 10) | Robustness |
| Feb 25, 2025 | OpenAI deep research system card | 67 | Automated evaluation for risky advice built from the targeted red teaming conversations, not_unsafe 0.67 (Table 8) | Robustness |
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% - DistressBench In use Models reply as a chatbot to 718 simulated users in psychological crisis, in single-turn and multi-turn chats. Three judge models score replies against clinician-written rubrics.
Muse Spark 1.2 88.4% - Lakera B3 (Backbone Breaker Benchmark) In use Crowdsourced prompt-injection attacks hit backbone LLMs inside agent threat snapshots at three defense levels. The score is attack resistance, 100 minus the board's vulnerability percentage. Claude Opus 4.5 89%
- IHEval In use Models face conflicts between system, user and tool instructions. Reports a composite score for following the higher-priority instruction. GPT-4o 70%