IFBenchBrowse 296

IFBench

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

Version not specifiedExact reported variant
Reasoning7 ranked models7 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-5.2OpenAI75.0%Reported configurationMiniMax report1 value · 1 reportFeb 12, 2026 · source
2Gemini 3 ProGoogle70.0%Reported configurationMiniMax report1 value · 1 reportFeb 12, 2026 · source
3MiniMax M2.1MiniMax70.0%Reported configurationMiniMax report1 value · 1 reportFeb 12, 2026 · source
4MiniMax M2.5MiniMax70.0%Reported configurationMiniMax report1 value · 1 reportFeb 12, 2026 · source
5Claude Opus 4.5Anthropic58.0%Reported configurationMiniMax report1 value · 1 reportFeb 12, 2026 · source
6Claude Sonnet 4.5Anthropic57.0%Reported configurationMiniMax report1 value · 1 reportFeb 12, 2026 · source
7Claude Opus 4.6Anthropic53.0%Reported configurationMiniMax report1 value · 1 reportFeb 12, 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