Claude 3.7 Sonnet (Thinking)
Release Date: 2/24/2025
Benchmarked by 
Hybrid reasoning agent, high intelligence, vision inputs, and fast code/content generation.
Avg. Accuracy
73.38%
Latency
69.63s
Cost (In/Out)
3 / 15
Context Window
200k
Max Output Tokens
8k
Input Modality
Hyperparameter settings
Default Provider :
N/A
Some benchmarks may use different provider and parameters. Please refer to the benchmark page for more information.
Temperature
1
Top P
Default
Top K
Default
Max Output Tokens
8,192
Benchmarks
Accuracy
Rankings
Academic Benchmarks
Proprietary Benchmarks (contact us to get access)