Related Models
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
48.1%
HLE
4.2%
LiveCodeBenchNot evaluated
SciCode
25.8%
TerminalBench Hard
2.3%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
44.4%
Long Context Recall
18.7%
Tau2
42.1%
Market AverageTop Score