LABBench2Browse 296

LABBench2

Can the model reason accurately about difficult scientific material?

Version not specifiedExact reported variant
Science7 ranked models10 reported values2 reportsHigher is better

Top rankings

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

7
RankModelBest scoreBest reported setting
1Gemini 3.8 FlashGoogle86.2%Reported configurationGoogle DeepMind report1 value · 1 reportSep 2, 2026 · source
2Claude Opus 5Anthropic84.2%Reported configurationGoogle DeepMind report1 value · 1 reportSep 2, 2026 · source
3Gemini 3.7 FlashGoogle82.1%Reported configurationGoogle DeepMind report2 values · 2 reportsSep 2, 2026 · source
4GPT-5.6 SolOpenAI82.1%Reported configurationGoogle DeepMind report1 value · 1 reportSep 2, 2026 · source
5GPT-5.6 TerraOpenAI81.2%Reported configurationGoogle DeepMind report2 values · 2 reportsSep 2, 2026 · source
6Claude Sonnet 5Anthropic80.1%Reported configurationGoogle DeepMind report2 values · 2 reportsSep 2, 2026 · source
7Gemini 3.6 FlashGoogle76.1%Reported configurationGoogle report1 value · 1 reportAug 13, 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.

Google-computed for Gemini and GPT-5.6 Terra with a Linux terminal, bioinformatics tools, Python, R, and internet access. Biology real-world research tasks; exact model-card cells.

Method / source