TAU2
Measured May 14, 2026Source
Score
0.65
Models15 0 
Claude 4 Sonnet (Reasoning)
AnthropicAnthropicUnited States
This is a mid-tier model from the Claude 4 series, optimized for advanced reasoning and chain-of-thought processing. It balances strong performance in complex problem-solving, code generation, and multimodal understanding with efficient speed and cost.
ReasoningCodingFastCheapMultimodalLong context
Input / 1M tokens
$3.75Output / 1M tokens
$15.00Output tokens/s
50.19First-token seconds
11.25sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.31
Lcr
Measured May 14, 2026Source
Score
0.65
Ifbench
Measured May 14, 2026Source
Score
0.55
Aime 25
Measured May 14, 2026Source
Score
0.74
Aime
Measured May 14, 2026Source
Score
0.77
Math 500
Measured May 14, 2026Source
Score
0.99
Scicode
Measured May 14, 2026Source
Score
0.4
Livecodebench
Measured May 14, 2026Source
Score
0.66
Hle
Measured May 14, 2026Source
Score
0.1
Gpqa
Measured May 14, 2026Source
Score
0.78
Mmlu Pro
Measured May 14, 2026Source
Score
0.84
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
74.3
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
34.1
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
38.7
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