AI Benchmark Model
Claude 3.7 Sonnet (Reasoning)
Benchmark scores, pricing, speed, and model comparisons for Claude 3.7 Sonnet (Reasoning).
Key scores
Review benchmark scores, pricing, performance data, and generated comparisons for this AI model.
Benchmark results
10 tracked benchmark rows for Claude 3.7 Sonnet (Reasoning).
MATH 500 Math
94.7% MMLU Pro Knowledge
83.7% GPQA Reasoning
77.2% AIME 2025 Math
56.3% TAU2 Other
54.7% AIME Math
48.7% IFBench Other
48.3% LiveCodeBench Code
47.3% TerminalBench Hard Other
21.2% HLE Other
9.7%