OpenAI Research Engineer Interview: Coding
Models solve 18 self-contained coding problems like those in OpenAI interviews. Scored as pass@1.
In-house OpenAI evaluation from the internal interview question bank.
- 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
- Code A program or patch run against tests.
o1 leads with 100% among models released by Apr 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 Apr 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 o1 100%
- 2 o4-mini 98%
- 3 o3 97%
- 4 GPT-4o May 2024 95%
- 5 o3-mini 92%
- 6 OpenAI deep research 79%
- 7 GPT-4.5 79%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o1 | 100% | Dec 2024 | Model card | |
| 2 | o4-mini | 98% | Apr 2025 | Model card | |
| 3 | o3 | 97% | Apr 2025 | Model card | |
| 4 | GPT-4o May 2024 | 95% | Aug 2024 | Model card | |
| 5 | o3-mini | 92% | Jan 2025 | Model card | |
| 6 | OpenAI deep research | 79% | Feb 2025 | Model card | |
| 7 | GPT-4.5 | 79% | Feb 2025 | Model card |
2 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.
The best score passed 85% in Aug 2024
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.
9 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 |
|---|---|---|---|---|
| 16 Apr 2025 | o4-mini system card | 98 | OpenAI RE Interview Coding, pass@1, o4-mini no browsing launch candidate, printed chart label (Figure 17) | AI R&D risk |
| 16 Apr 2025 | o3 system card | 97 | OpenAI RE Interview Coding, pass@1, o3 no browsing launch candidate, printed chart label (Figure 17) | AI R&D risk |
| 27 Feb 2025 | GPT-4.5 system card | 79 | OpenAI Research Engineer Interview, coding questions (4.6.1) | Autonomy |
| 25 Feb 2025 | OpenAI deep research system card | 79 | OpenAI RE Interview Coding, pass@1, post-mitigation with browsing, text and printed chart label (without browsing 86%) (3.4.7) | Autonomy |
| 31 Jan 2025 | o3-mini system card | 92 | OpenAI RE Interview Coding, pass@1, post-mitigation (5.7.1) | Autonomy |
| 5 Dec 2024 | o1 system card | 100 | OpenAI RE Interview Coding, pass@128 as the card reports (pass@1 83%), o1 (post-mitigation), printed chart label (5.8.1) | Autonomy |
| 12 Sep 2024 | o1-preview system card | OpenAI Research Engineer Interviews (Coding), pass@1 and pass@128, chart without printed numbers (4.5.1) | Autonomy | |
| 12 Sep 2024 | o1-mini system card | OpenAI Research Engineer Interviews (Coding), pass@1 and pass@128, chart without printed numbers (4.5.1) | Autonomy | |
| 8 Aug 2024 | GPT-4o system card | 95 | OpenAI research coding interview, pass@100 (3.8) | AI R&D risk |
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%