Skip to main content
Benchmark Registry
ModelsBenchmarksOrganizationsCompare

MMLU-Pro

Benchmark
MMLU-Pro
Evaluated by
Qwen Team
Release date
June 3, 2024
Version
MMLU-Pro Original
Metric
Accuracy

Results

2 results

LatestHistory
All providersAlibaba (Tongyi)DeepSeek AIGoogle (DeepMind)Microsoft AIMistral AIMoonshot AINVIDIAZ.ai
MMLU-Pro Original results
ProviderModelScoreSourceRegistry No.
Mistral AIMistral Small 4 (high)78.0%Source for Mistral Small 4 (high) on MMLU-Pro Original (opens in a new tab)90004
Mistral AIMistral Small 4 (none)73.5%Source for Mistral Small 4 (none) on MMLU-Pro Original (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