Community Benchmarks Leaderboard
Unified leaderboard for the official Hugging Face benchmarks. A place to find and compare results comming from the commmunity, model card, paper.
📐
Math
🧠
Knowledge
| Model↕ |
GSM8K ℹ️↕ |
MMLU-Pro ℹ️↕ |
GPQA◆ ℹ️↕ |
HLE ℹ️↕ |
olmOCR ℹ️↕ |
SWE-V ℹ️↕ |
ArguAna ℹ️↕ |
SWE-Pro ℹ️↕ |
AIME'26 ℹ️↕ |
TB 2.0 ℹ️↕ |
EvasionB ℹ️↕ |
HMMT Feb'26 ℹ️↕ |