TAU2
Measured Jul 10, 2026Source
Score
0.7
Models15 0 
Claude 4.5 Sonnet (Non-reasoning)
AnthropicAnthropicUnited States
This is the non-reasoning variant of Anthropic's Claude 4.5 Sonnet model. It is optimized for high-speed, cost-effective responses while maintaining strong performance in coding, instruction following, and general knowledge tasks. It is suitable for applications requiring quick, high-quality outputs without extended chain-of-thought reasoning.
CodingFastCheapLong context
Input / 1M tokens
$3.00Output / 1M tokens
$15.00Output tokens/s
48.15First-token seconds
1.44sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured Jul 10, 2026Source
Score
0.29
Lcr
Measured Jul 10, 2026Source
Score
0.51
Ifbench
Measured Jul 10, 2026Source
Score
0.43
Aime 25
Measured Jul 10, 2026Source
Score
0.37
Scicode
Measured Jul 10, 2026Source
Score
0.43
Livecodebench
Measured Jul 10, 2026Source
Score
0.59
Hle
Measured Jul 10, 2026Source
Score
0.07
Gpqa
Measured Jul 10, 2026Source
Score
0.73
Mmlu Pro
Measured Jul 10, 2026Source
Score
0.86
Artificial Analysis Math Index
Measured Jul 10, 2026Source
Score
37
Artificial Analysis Intelligence Index
Measured Jul 10, 2026Source
Score
29.3
Tau Banking
Measured Jul 10, 2026Source
Score
0.19
Terminalbench V2 1
Measured Jul 10, 2026Source
Score
0.56
Artificial Analysis Coding Index
Measured Jul 10, 2026Source
Score
52.1
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server