MLS-Bench (Vanilla): leaderboard
MLS-Bench (Vanilla) scores the first proposal each model tests when a model must invent a better ML method inside a frozen research codebase, over 140 tasks in 12 research areas of MLS-Bench (2026). Each task score is normalized so the worst reproduced human baseline is 0 and the best is 50, on a 0 to 100 scale where higher is better; the board averages the 12 area scores.
Metric: Mean of the 12 area scores, each the mean normalized task score (0-100): each metric is anchored so the worst reproduced human baseline scores 0 and the best 50 (a metric's theoretical optimum maps to 100), metrics are averaged with human weights within a setting and by geometric mean across at least three generalization settings, over the 140 method-invention tasks of MLS-Bench (the full set, not MLS-Bench-Lite); Vanilla protocol: the score of the model's first tested proposal (tools: edit, test, submit, undo); high reasoning effort with a 10,000-token thinking budget, web search disabled, fixed seeds; higher is better. Source: arxiv.org. Saturation forecast: Around August 2028. 5 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.6 | Thinking | 28.1 | #114 |
| 2 | Gemini 3.1 Pro (Preview) | High | 26.5 | #102 |
| 3 | GPT-5.4 | High | 19.5 | #138 |
| 4 | DeepSeek V3.2 | Thinking | 18.1 | #425 |
| 5 | Qwen 3.6 Plus | Thinking | 16.5 | #245 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mls-bench-vanilla · How It Works · Data refreshed daily, snapshot 2026-11-22.