CritPtBrowse 296

CritPt

Can the model reason accurately about difficult scientific material?

Version not specifiedExact reported variant
Science8 ranked models8 reported values1 reportsHigher is better

Top rankings

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

8
RankModelBest scoreBest reported setting
1GPT-5.5OpenAI27.1%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
2Claude Opus 4.8Anthropic20.9%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
3GLM-5.2Z.ai20.9%max effortZ.ai report1 value · 1 reportJun 16, 2026 · source
4Gemini 3.1 ProGoogle17.7%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
5Qwen3.7-MaxQwen13.4%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
6DeepSeek V4 ProDeepSeek12.9%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
7GLM-5.1Z.ai4.6%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
8MiniMax M3MiniMax3.7%Reported configurationZ.ai report1 value · 1 reportJun 16, 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 reason accurately about difficult scientific material?

Scientific knowledge and reasoning under the benchmark's published question set. 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