TAU2
Measured Jul 10, 2026Source
Score
0.5
Models15 1 
Claude 3.7 Sonnet (Non-reasoning)
AnthropicAnthropicUnited States
Claude 3.7 Sonnet (Non-reasoning) is a variant of the Claude 3.7 Sonnet model optimized for speed and cost-efficiency, while retaining strong performance in coding, multimodal understanding, and long-context tasks. It is designed for applications where rapid response and lower latency are prioritized over extended chain-of-thought reasoning.
CodingFastCheapLong contextMultimodal
Input / 1M tokens
$3.00Output / 1M tokens
$15.00Supported plans
1Benchmark history
Evaluations
Terminalbench Hard
Measured Jul 10, 2026Source
Score
0.21
Lcr
Measured Jul 10, 2026Source
Score
0.48
Ifbench
Measured Jul 10, 2026Source
Score
0.44
Aime 25
Measured Jul 10, 2026Source
Score
0.21
Aime
Measured Jul 10, 2026Source
Score
0.22
Math 500
Measured Jul 10, 2026Source
Score
0.85
Scicode
Measured Jul 10, 2026Source
Score
0.38
Livecodebench
Measured Jul 10, 2026Source
Score
0.39
Hle
Measured Jul 10, 2026Source
Score
0.05
Gpqa
Measured Jul 10, 2026Source
Score
0.66
Mmlu Pro
Measured Jul 10, 2026Source
Score
0.8
Artificial Analysis Math Index
Measured Jul 10, 2026Source
Score
21
Artificial Analysis Intelligence Index
Measured Jul 10, 2026Source
Score
23.5
Artificial Analysis Coding Index
Measured Jul 10, 2026Source
Score
36.4
Plan availability
Products and plans that support this model
ZenMux Builder
ZenMux Builder
ZenMux is a unified API gateway that provides access to over 100 AI models from providers like OpenAI, Anthropic, Google, and xAI through a single account and API. It offers subscription plans (Builder Plan) for personal development, vibe coding, and testing, as well as pay-as-you-go for production use. The platform supports coding agents like Claude Code and OpenClaw, and provides automatic model routing, multi-provider failover, and AI quality insurance compensation.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server