MLE-BenchBrowse 296

MLE-Bench

Can the model complete substantial programming work under this benchmark's agent setup?

Version not specifiedExact reported variant
Coding6 ranked models6 reported values1 reportsHigher is better

Top rankings

One row per model, using its best reported score across effort settings.

6
RankModelBest scoreBest reported setting
1Claude Sonnet 5Anthropic66.9%Reported configurationGoogle report1 value · 1 reportJul 21, 2026 · source
2Gemini 3.6 FlashGoogle63.9%Reported configurationGoogle report1 value · 1 reportJul 21, 2026 · source
3Gemini 3.5 FlashGoogle49.7%Reported configurationGoogle report1 value · 1 reportJul 21, 2026 · source
4GPT-5.6 LunaOpenAI47.6%Reported configurationGoogle report1 value · 1 reportJul 21, 2026 · source
5Grok 4.5SpaceXAI43.2%Reported configurationGoogle report1 value · 1 reportJul 21, 2026 · source
6Gemini 3.1 ProGoogle42.6%Reported configurationGoogle report1 value · 1 reportJul 21, 2026 · source

Effort curve

Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.

0
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology

Can the model complete substantial programming work under this benchmark's agent setup?

Software implementation, debugging, or repository work under the published evaluation protocol. Higher is better. The value is the percentage reported in this lab's table.

Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.

Method / source