Related Models
Benchmarks
MMLU-Pro
76.8%
GPQA Diamond
57.8%
HLE
5.7%
LiveCodeBench
46.2%
SciCode
16.4%
TerminalBench HardNot evaluated
MATH-500
90.0%
AIME
66.3%
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2Not evaluated
Market AverageTop Score