Related Models
Benchmarks
MMLU-Pro
74.2%
GPQA Diamond
60.3%
HLE
4.9%
LiveCodeBench
57.6%
SciCode
32.3%
TerminalBench HardNot evaluated
MATH-500
94.4%
AIME
60.3%
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2Not evaluated
Market AverageTop Score