HMMT 2026 FebBrowse 296

HMMT 2026 Feb

Can the model solve difficult problems that require more than factual recall?

Version not specifiedExact reported variant
Reasoning7 ranked models11 reported values1 reportsHigher is better

Top rankings

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

7
RankModelBest scoreBest reported setting
1GPT-5.4OpenAI97.7%xhigh effortDeepSeek report1 value · 1 reportApr 26, 2026 · source
2Claude Opus 4.6Anthropic96.2%max effortDeepSeek report1 value · 1 reportApr 26, 2026 · source
3DeepSeek V4 ProDeepSeek95.2%max effortDeepSeek report3 values · 1 reportApr 26, 2026 · source
4DeepSeek-V4-FlashDeepSeek94.8%max effortDeepSeek report3 values · 1 reportApr 26, 2026 · source
5Gemini 3.1 ProGoogle94.7%high effortDeepSeek report1 value · 1 reportApr 26, 2026 · source
6Kimi K2.6Moonshot AI92.7%Reported configurationDeepSeek report1 value · 1 reportApr 26, 2026 · source
7GLM-5.1Z.ai89.4%Reported configurationDeepSeek report1 value · 1 reportApr 26, 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 solve difficult problems that require more than factual recall?

Multi-step reasoning on academic, mathematical, or abstract problems. 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.

Frontier comparison and across-modes table.

Method / source