Benchmarks
MMLU-Pro
39.7%
GPQA Diamond
33.1%
HLE
6.6%
LiveCodeBench
9.3%
SciCode
11.8%
TerminalBench HardNot evaluated
MATH-500
27.9%
AIME
3.0%
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2Not evaluated
Market AverageTop Score