GeneBench ProBrowse 296

GeneBench Pro

Can the model reason accurately about difficult scientific material?

Version not specifiedExact reported variant
Science7 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-5.6 SolOpenAI28.70%Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source
2GPT-5.6 TerraOpenAI23.30%Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source
3Claude Opus 4.8Anthropic16.00%Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source
4GPT-5.5OpenAI12.00%Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source
5GPT-5.6 LunaOpenAI10.80%Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source
6Gemini 3.5 FlashGoogle8.14%Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source
7Gemini 3.1 Pro PreviewGoogle3.10%Reported configurationOpenAI report1 value · 1 reportJul 9, 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