IMOAnswerBenchBrowse 296

IMOAnswerBench

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

Version not specifiedExact reported variant
Reasoning14 ranked models17 reported values3 reportsHigher is better

Top rankings

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

14
RankModelBest scoreBest reported setting
1GLM-5.2Z.ai91.0%max effortZ.ai report1 value · 1 reportJun 16, 2026 · source
2Qwen3.7-MaxQwen90.0%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
3DeepSeek V4 ProDeepSeek89.8%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
4Claude Opus 4.5Anthropic84.0%Reported configurationQwen report1 value · 1 reportApr 21, 2026 · source
5GLM-5.1Z.ai83.8%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
6Claude Opus 4.8Anthropic83.5%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
7Gemini 3.1 ProGoogle81.0%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
8Qwen3.5-397B-A17BQwen80.9%Reported configurationQwen report1 value · 1 reportApr 21, 2026 · source
9Qwen3.6-27BQwen80.8%Reported configurationQwen report1 value · 1 reportApr 21, 2026 · source
10Qwen3.5-27BQwen79.9%Reported configurationQwen report2 values · 2 reportsApr 21, 2026 · source
11Qwen3.6-35B-A3BQwen78.9%Reported configurationQwen report2 values · 2 reportsApr 21, 2026 · source
12Qwen3.5-35B-A3BQwen76.8%Reported configurationQwen report1 value · 1 reportApr 15, 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.

Method / source