MLS-Bench (Vanilla) - Trustworthy Learning: leaderboard

MLS-Bench (Vanilla) Trustworthy Learning scores the first proposal each model tests on the 8 Trustworthy Learning tasks of MLS-Bench (2026), where a model must invent a better ML method inside a frozen research codebase. Task scores are normalized so the worst reproduced human baseline is 0 and the best is 50, on a 0 to 100 scale where higher is better.

Metric: 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 8 MLS-Bench tasks of the Trustworthy Learning area; 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 February 2028. 5 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-5.4High31.8#135
2Gemini 3.1 Pro (Preview)High30.1#99
3Claude Opus 4.6Thinking26.7#113
4Qwen 3.6 PlusThinking24.4#238
5DeepSeek V3.2Thinking16.4#419

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=mls-bench-vanilla-trustworthy-learning · How It Works · Data refreshed daily, snapshot 2026-11-21.