0

Claude Sonnet 4.5 vs GPT-5

Head to head on 31 shared benchmarks, with price, context window, and release dates.

Benchmark scores

113

evals · sort by any column, ⤢ to expand fullscreen

Model
GPT-5

OpenAI

46.7%48.3%61.1%1623elo72.832.4%83.3%68.6%6.6%45.0%83.4%58.2%54.3%0.521.6286.1%49.6%83.7%82.0%65.5%0.0%18.0%43.7%37.8%74.9%74.4%73.4%12.9%20.1%54.8%0.0%91.1%-88.0%94.6%---0.0%--0.150.0%68.1%4.58---57.7%80.0%80.0%----91.7%-0.0%88.9%----100.0%--48.9%---------37.5%100.0%-0.0%92.7%92.7%-93.3%10.0%0.0%-60.0%-0.26-------------2.34---87.5%-0.8690.0%90.0%-56.7%
Claude Sonnet 4.5

Anthropic

0.0%37.0%60.8%1675elo71.415.2%83.9%72.7%7.2%42.7%83.8%0.0%59.0%0.750.750.0%40.6%84.5%86.0%64.0%0.0%19.0%32.9%42.8%77.2%74.8%73.3%28.8%22.6%0.0%70.5%-0.0%--1000.0%0.0%-0.0%5.0%----0.0%0.0%0.0%---0.0%0.0%0.0%0.0%-0.0%--0.0%0.0%0.0%0.0%-0.0%0.0%-87.5%0.0%70.7%80.4%57.0%53.4%76.5%79.3%77.6%--0---0---0.0%-0.0%-62.9%0.0%0.0%0.0%0.0%0.0%0.0%0.0%00.0%0.0%67.0%0.0%-0050.34-0---1.4927.5%
2 / 2 models
AttributeClaude Sonnet 4.5

Anthropic

GPT-5

OpenAI

Descriptionanthropic/claude-sonnet-4.5 is an AI model.OpenAI's August 2025 unified frontier model that auto-routes between a fast model and a deeper "thinking" variant.
FamilyClaudeGPT 5
ParamsUndisclosed (closed)Undisclosed (closed)
Open weightsclosedclosed
LicenseProprietaryProprietary
Released29 Sep 20257 Aug 2025
Context1,000,000400,000
Input $/1M$3.00-
Output $/1M$15.00-
Cache read $/1M$0.300$0.125
Cache write $/1M$3.750-
Speed0 tok/s0 tok/s
Latency0.00 s0.00 s
Modalitiestext, image, filetext, image, file
Providersanthropic, aws-bedrock, vertex-aiopenai
PublisherAnthropicOpenAI
Reported scores
LiveBench - Math79.3% (LiveBench)
LiveBench - Coding80.4% (LiveBench)
LiveBench - Language76.5% (LiveBench)
LiveBench - Data Analysis57.0% (LiveBench)

FAQ

Is Claude Sonnet 4.5 or GPT-5 better?
Across the 31 benchmarks both models report on Sophon, Claude Sonnet 4.5 leads on 16 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
How do Claude Sonnet 4.5 and GPT-5 compare on GPQA Diamond?
Claude Sonnet 4.5 scores 72.7% and GPT-5 scores 68.6% on GPQA Diamond.
When were Claude Sonnet 4.5 and GPT-5 released?
Claude Sonnet 4.5 was released 29 Sep 2025 by Anthropic. GPT-5 was released 7 Aug 2025 by OpenAI.

Comparing something else? Build your own side-by-side.