Agentic tasks (autonomous replication and adaptation)
Agents attempt resource acquisition tasks such as building an authenticated API proxy or loading a model on a cloud account. Scored as success rate.
In-house OpenAI Preparedness evaluation. Includes simplified variants with hints.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
OpenAI deep research leads with 78% among models released by Feb 2025
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.
The newest model with a score here came out in Feb 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 OpenAI deep research 78%
- 2 GPT-4.5 40%
- 3 o3-mini 27%
- 4 GPT-4o May 2024 0%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | OpenAI deep research | 78% | Feb 2025 | Model card | |
| 2 | GPT-4.5 | 40% | Feb 2025 | Model card | |
| 3 | o3-mini | 27% | Jan 2025 | Model card | |
| 4 | GPT-4o May 2024 | 0% | Aug 2024 | Model card |
3 models have held number one since its release in Aug 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
8 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 |
|---|---|---|---|---|
| 27 Feb 2025 | GPT-4.5 system card | 40 | Agentic Tasks, post-mitigation (4.6.3) | Autonomy |
| 25 Feb 2025 | OpenAI deep research system card | 78 | Agentic Tasks, agentic subtasks pass@1, post-mitigation with browsing, printed chart label (without browsing 80%) (3.4.7) | Autonomy |
| 31 Jan 2025 | o3-mini system card | 27 | Agentic Tasks, pass@1, o3-mini (Post), printed chart label (5.7.3) | Autonomy |
| 23 Jan 2025 | OpenAI Computer-Using Agent (CUA) system card | Autonomous replication eval in computer use, pre-mitigation Operator model, main tasks OpenAI API proxy 0%, GPU acquisition 60%, Mistral 7B docker 0% (prompt engineered 0%, 80%, 0%), no overall score (Table 2, 3.3.2) | Autonomy | |
| 5 Dec 2024 | o1 system card | Agentic Tasks, success rate over 100 trials on 10 tasks plus buy_gpu with Ranger browsing (8%), no overall score (5.8.3 charts) | Autonomy | |
| 12 Sep 2024 | o1-preview system card | Agentic Tasks: Success rates over 100 trials on 11 tasks, chart without printed numbers (4.5.3) | Autonomy | |
| 12 Sep 2024 | o1-mini system card | Agentic Tasks: Success rates over 100 trials on 11 tasks, chart without printed numbers (4.5.3) | Autonomy | |
| 8 Aug 2024 | GPT-4o system card | 0 | Autonomous replication and adaptation (ARA) tasks, 100 trials (3.8) | Autonomy |
More in AI research
- MLS-Bench In use Agent must invent one algorithmic change in an ML research scaffold whose gain transfers across settings. Scored relative to human baselines. Claude Fable 5.1 50.3%
- PaperBench In use Agent replicates ICML 2024 papers from scratch. LLM judge grades against author-written hierarchical rubrics.
Qwen 3.8 Max 93% - MLE-bench In use Kaggle-style ML engineering competitions. Agent trains models and is scored against competition leaderboards. GPT-6 Astra 93.8%
- PostTrainBench 1.2 In use CLI agent gets a base model, one H100 and a time budget to post-train it for a target benchmark. Scored on normalized gain. Claude Fable 5.1 44.6%
- KernelBench In use Replace PyTorch operators with faster custom GPU kernels. Scored on correctness and speedup.
MiniMax-M3 28.8% - OpenAI PRs Only in system cards Agents replicate internal OpenAI pull requests from a pre-PR branch and a prompt. Graded by hidden unit tests as pass@1. GPT-5.2 55%