This website uses cookies for authentication, support chat, and analytics. Only authentication cookies are turned on by default.
Animate this data
Bar chart race of Mistral AI, OpenAI, Google DeepMind and 7 more, by GPQA Diamond.
Create it free
Takes a free account
Mistral AI
Adversarial Nli
0.55 %
Aider Polyglot
0.11 %
Ale bench
763.98
Arc Agi
0.06 %
BALROG
0.18 %
Bbh
0.56 %
Bool Q
0.87 %
Chess Puzzles
0.03 %
Critpt
0.00 %
Dtbench
0.75 %
Enigma Eval
0.01 %
Forecastbench
0.57 %
FrontierCode
0.08 %
FrontierMath
0.00 %
GPQA Diamond
0.60 %
Gsm8k
0.84 %
Hella Swag
0.87 %
Hle
0.05 %
Lech Mazur Writing
0.08 %
Live bench
0.48 %
Lmca
0.26 %
Math Level 5
0.82 %
Mmlu
0.80 %
Open Book Qa
0.86 %
OTIS Mock AIME 2024 2025
0.32 %
Piqa
0.84 %
Proofbench
0.09 %
SciCode
0.40 %
SimpleBench
0.23 %
Surface Evolver bench
0.27 %
Trivia Qa
0.82 %
WebDev Arena
1,265.04
WeirdML
0.44 %
Wino Grande
0.77 %
Training Compute
2,340,000,000,000.00T FLOP
Mistral AI benchmark results over time.