Claude 3.7 Sonnet
Feb 2025
Claude 3.7 SonnetCompare inon
Benchmarks of 3.7 Sonnet27
BenchmarkByScoreRank
Math5
Multimodal2
Writing15
Health & law1
Legacy · saturated or no longer reported4
No benchmark matches
—per task?
price not verifiedprice
—output speed?
—context
Rankingin thinking mode?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunamaxwins 52%—$0.068Function calling only with none · Chat Completions+3
OpenKimi K3maxwins 60%—$2.00Sampling parameters are fixed+3BetterGPT-5.6 Lunaxhighwins 52%—$0.085BetterGPT-5.6 Terraxhighwins 55%—$0.63Prompts with >272K input tokensBetterGPT-6.1 Solmaxwins 59%—$0.72Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunamaxwins 52%—$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighwins 52%—$0.085GPT-5.6 Terraxhighwins 55%—$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 59%—$0.72Remove unsupported parameters+5GPT-6 Solmaxwins 56%—$1.04ModelScoreCostPer taskWhat changes
Kimi K3maxOpenwins 60%—$2.00Sampling parameters are fixed+3
GLM 5.2maxOpenwins 59%—$1.28No image inputGLM 5.3maxOpenwins 59%—$2.01No image input+4GLM 5unstatedOpenwins 58%—$1 / $3.20No image inputGLM 5.1unstatedOpenwins 58%—$1.40 / $4.40No image inputModelScoreCostPer taskWhat changes
Claude Opus 5.5highwins 67%—$1.82No forced tool use+5Claude Fable 5highwins 65%—$10 / $50Claude Opus 4.6highwins 65%—$5 / $25Claude Opus 4.7highwins 63%—$5 / $25Claude Fable 5.1maxwins 63%—$7.63Replace forced tool_choice+5Claude Opus 5maxwins 61%—$5.86Claude Opus 4.8highwins 61%—$5 / $25Claude Opus 4.5highwins 61%—$5 / $25All Anthropic models →History
7 versionsBenchmarks
all categoriesChat & Knowledge
Arena Text · overall1,388
Arena Text · Chinese1,298.6
Arena Text · English1,326.3
Arena Text · French1,288.4
Arena Text · German1,300.8
Arena Text · Japanese1,266.6
Arena Text · Korean1,248.8
Arena Text · Polish1,284.3
Arena Text · Russian1,310.7
Arena Text · Spanish1,298.5
Writing & Language
Vision & Documents
Arena Vision · overall1,168.9
FAQ
How much does Claude 3.7 Sonnet cost?›
There is no per-unit API price: price not verified.
When was Claude 3.7 Sonnet released? Is there a newer version?›
Released 2025-02-24. It has been superseded by Claude Sonnet 5.5.
Can Claude 3.7 Sonnet read images?›
It accepts text and images as input.
What is Claude 3.7 Sonnet?›
Claude 3.7 Sonnet is a language model from Anthropic, released Feb 2025.
What are the best alternatives to Claude 3.7 Sonnet?›
GPT-6 Luna (better), Kimi K3 (open weights).