TAU2
Measured May 14, 2026Source
Score
0.55
Models15 0 
Claude 3.7 Sonnet (Reasoning)
AnthropicAnthropicUnited States
Claude 3.7 Sonnet (Reasoning) is an enhanced version of the Sonnet model optimized for complex reasoning tasks. It features an extended thinking mode for deeper, step-by-step analysis and excels at handling long-context, multimodal inputs, and coding challenges.
ReasoningCodingLong contextMultimodal
Input / 1M tokens
$0.00Output / 1M tokens
$0.00Supported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.21
Lcr
Measured May 14, 2026Source
Score
0.61
Ifbench
Measured May 14, 2026Source
Score
0.48
Aime 25
Measured May 14, 2026Source
Score
0.56
Aime
Measured May 14, 2026Source
Score
0.49
Math 500
Measured May 14, 2026Source
Score
0.95
Scicode
Measured May 14, 2026Source
Score
0.4
Livecodebench
Measured May 14, 2026Source
Score
0.47
Hle
Measured May 14, 2026Source
Score
0.1
Gpqa
Measured May 14, 2026Source
Score
0.77
Mmlu Pro
Measured May 14, 2026Source
Score
0.84
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
56.3
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
27.6
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
34.7
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
Discussion
Thinking... Make sure you are connected to GitHub server