Skip to content

STEMBench120: six-domain scientific research progress

Scores how far a model advances 120 open research tasks across biology, chemistry, physics, astronomy, Earth science and engineering on a 0 to 4 progress scale, crediting supported partial work and honest statements of what remains unresolved.

9 models

Higher is better.

  1. 1GPT-6 AstraOpenAI2.81
  2. 2GPT-6.1 SolOpenAI2.76
  3. 3Muse WonderMeta2.68
  4. 4Claude Opus 5.5Anthropic2.62
  5. 5Hy4 previewTencent2.59
  6. 6Mistral Large 4Mistral2.50
  7. 7DeepSeek V4.1 Flash 1017DeepSeek2.49
  8. 8Gemini 4 ArgonGoogle2.44
  9. 9MiMo-V2.6-ProXiaomi2.17
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Audited progress level 0 to 4 per task, refined to a fractional score; complete-run mean across all tasks
Tasks
120 research tasks, 20 in each of six STEM domains
Authors
Ulam (2026)

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.