MLE-bench 30
Agents train models for 30 of MLE-bench's Kaggle-style competitions. The score is the share of runs that earn a bronze medal or better.
OpenAI's system cards report this subset, and Meta reports a 30-task subset in its preparedness reports. It has no public leaderboard.
- Made by
- OpenAI
- Released
- August 2025
- Kind
- Machine learning engineering
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Strongest model tested
- GPT-5.5 #20 on the capability index
- Last in a system card
- June 2026
- Last model added
- June 2026
In the authors’ words
We introduce MLE-bench, a benchmark for measuring how well AI agents perform at machine learning engineering. To this end, we curate 75 ML engineering-related competitions from Kaggle, creating a diverse set of challenging tasks that test real-world ML engineering skills such as training models, preparing datasets, and running experiments. We establish human baselines for each competition using Kaggle's publicly available leaderboards. We use open-source agent scaffolds to evaluate several frontier language models on our benchmark, finding that the best-performing setup–OpenAI's o1-preview with AIDE scaffolding–achieves at least the level of a Kaggle bronze medal in 16.9% of competitions. In addition to our main results, we investigate various forms of resource scaling for AI agents and the impact of contamination from pre-training. We open-source our benchmark code (github.com/openai/mle-bench/) to facilitate future research in understanding the ML engineering capabilities of AI agents.
GPT-5.5 leads with 36.7% among models released by April 2026
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 April 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 15 more
- 1 GPT-5.5 36.7%
- 2 GPT-5.4 23.3%
- 3 GPT-5.1-Codex-Max 17%
- 4 GPT-5.2 16%
- 5
Muse Spark 15.8% - 6 GPT-5.2 Codex 10%
- 7 GPT-5 8.00%
- 8 GPT-5 mini 3.00%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.5 | 36.7% | Apr 2026 | Lab model card | |
| 2 | GPT-5.4 | 23.3% | Mar 2026 | Lab model card | |
| 3 | GPT-5.1-Codex-Max | 17% | Nov 2025 | Lab model card | |
| 4 | GPT-5.2 | 16% | Dec 2025 | Lab model card | |
| 5 | Muse Spark | 15.8% | Jun 2026 | Lab model card | |
| 6 | GPT-5.2 Codex | 10% | Dec 2025 | Lab model card | |
| 7 | GPT-5 | 8.00% | Aug 2025 | Lab model card | |
| 8 | GPT-5 mini | 3.00% | Aug 2025 | Lab model card |
4 models have held number one in labs’ own numbers since its release in August 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
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.
8 system cards report it, from 2 labs
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 |
|---|---|---|---|---|
| Jun 12, 2026 | Muse Spark system card | 15.8 | MLE-Bench any medal rate, 30-task subset, 24 hours (Table 1, Table 11) | AI R&D risk |
| Apr 23, 2026 | GPT-5.5 system card | 36.7 | MLE-Bench-30 (30-competition subset), bronze or better, pass@1, printed chart label (Figure 19, 9.1.3.2) | AI R&D risk |
| Mar 5, 2026 | GPT-5.4 system card | 23.3 | MLE-Bench (30-competition subset), pass@1, printed chart label (Figure 16, 5.1.3.2) | AI R&D risk |
| Dec 18, 2025 | GPT-5.2 Codex system card addendum | 10 | MLE-Bench-30 (30-competition subset), bronze pass@1, printed chart label (Figure 10, 5.1.3.2) | AI R&D risk |
| Dec 11, 2025 | GPT-5.2 system card addendum | 16 | MLE-Bench-30, 30-competition subset, bronze pass@1, no browsing, printed chart label (Figure 14) | AI R&D risk |
| Nov 18, 2025 | GPT-5.1-Codex-Max system card | 17 | MLE-Bench-30 (30-competition subset), bronze pass@1, printed chart label (Figure 12, 5.1.3.3) | AI R&D risk |
| Aug 7, 2025 | GPT-5 system card | 8 | MLE-Bench-30, bronze pass@1, no browsing launch candidate (Figure 23) | AI R&D risk |
| Aug 7, 2025 | GPT-5 mini system card | 3 | MLE-Bench-30, bronze pass@1, gpt-5-thinking-mini launch candidate (Figure 23) | AI R&D risk |
More in AI research
- PaperBench In use Agent replicates ICML 2024 papers from scratch. LLM judge grades against author-written hierarchical rubrics.
Qwen 3.8 Max 93% - 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%
- 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%
- MLE-bench In use Kaggle-style ML engineering competitions. Agent trains models and is scored against competition leaderboards. GPT-6 Astra 93.8%
- KernelBench In use Replace PyTorch operators with faster custom GPU kernels. Scored on correctness and speedup.
MiniMax-M3 28.8% - PMPP-Hard In use Agents write GPU kernels for 69 tasks that must be correct, and on 48 of them also run within 1.25 times the reference time. The score is the area under the solved-tasks curve over a 10-hour budget, out of 690 task-hours.
Inkling 2 Small 494.3