Skip to main content
Benchmark Registry
ModelsBenchmarksOrganizations

GPQA

Graduate-Level Google-Proof Q&A

Benchmark
GPQA
Evaluated by
GPQA Authors
Release date
November 20, 2023
Version
GPQA Diamond
Metric
GPQA Diamond Accuracy

Results

2 results

LatestHistory
All providersAlibaba (Tongyi)AnthropicDeepSeek AIGoogle (DeepMind)Microsoft AIMistral AIMoonshot AINVIDIAOpenAIThinking Machines LabZ.ai
Graduate-Level Google-Proof Q&A Diamond results
ProviderModelScoreSourceRegistry No.
Mistral AIMistral Small 4 (none)59.1%Source for Mistral Small 4 (none) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab)90004
Mistral AIMistral Small 4 (high)71.2%Source for Mistral Small 4 (high) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab)90004
Page 1 of 1

© 2026 Densa Labs

Toggle between the data update date and the application build time.
Legal
Color theme