Claude 3.5 Sonnet
Claude 3.5 SonnetCompare inon
Benchmarks of 3.5 Sonnet10
BenchmarkByScoreRank
Multimodal1
Writing1
Legacy · saturated or no longer reported8
No benchmark matches
—per task?
price not verifiedprice
—output speed?
—context
Ranking?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
BetterClaude Opus 5unstated+48%—$5 / $25
OpenGLM 5.3unstated+40%—$1.40 / $4.40No image input+4BetterClaude Fable 5.1unstated+46%—$10 / $50Replace forced tool_choice+5BetterClaude Opus 5.5unstated+45%—$4 / $20No forced tool use+5BetterClaude Fable 5unstated+42%—$10 / $50ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
Claude Opus 5unstated+48%—$5 / $25Claude Fable 5.1unstated+46%—$10 / $50Replace forced tool_choice+5Claude Opus 5.5unstated+45%—$4 / $20No forced tool use+5Claude Fable 5unstated+42%—$10 / $50
Grok 4.7unstated+42%—$2 / $6Reasoning cannot be disabled+4ModelScoreCostPer taskWhat changes
GLM 5.3unstatedOpen+40%—$1.40 / $4.40No image input+4
Kimi K3unstatedOpen+36%—$3 / $15Sampling parameters are fixed+3Kimi K2.6unstatedOpen+34%—$0.95 / $4GLM 5.2unstatedOpen+33%—$1.40 / $4.40No image input
DeepSeek V4 Pro 0813unstatedOpen+29%—$1.32 / $3.96No image input+5ModelScoreCostPer taskWhat changes
Claude Opus 5unstated+48%—$5 / $25Claude Fable 5.1unstated+46%—$10 / $50Replace forced tool_choice+5Claude Opus 5.5unstated+45%—$4 / $20No forced tool use+5Claude Fable 5unstated+42%—$10 / $50Claude Opus 4.7unstated+40%—$5 / $25Claude Opus 4.8unstated+38%—$5 / $25Claude Sonnet 4.6unstated+37%—$3 / $15Claude Sonnet 5unstated+34%—$2 / $10All Anthropic models →Benchmarks
all categoriesChat & Knowledge
Coding
SWE-rebench · all · May 1, 2025 to September 1, 202530.3
SWE-rebench · Go · May 1, 2025 to September 1, 20250
SWE-rebench · Java · May 1, 2025 to September 1, 20250
SWE-rebench · Rust · May 1, 2025 to September 1, 20250
SWE-rebench · Python · May 1, 2025 to September 1, 202530.3
SWE-rebench · TypeScript · May 1, 2025 to September 1, 20250
Writing & Language
Vision & Documents
VideoMMMUlab65.8
FAQ
How much does Claude 3.5 Sonnet cost?›
There is no per-unit API price: price not verified.
When was Claude 3.5 Sonnet released? Is there a newer version?›
It has been superseded by Claude Sonnet 5.5.
Can Claude 3.5 Sonnet read images?›
It accepts text and images as input.
What is Claude 3.5 Sonnet?›
Claude 3.5 Sonnet is a language model from Anthropic.
What are the best alternatives to Claude 3.5 Sonnet?›
Claude Opus 5 (better), GLM 5.3 (open weights).