0

Claude Sonnet 4.5 vs GPT-4.1 Mini

Head to head on 35 shared benchmarks, with price, context window, and release dates.

Benchmark scores

186

evals · sort by any column, ⤢ to expand fullscreen

Model
GPT-4.1 Mini

OpenAI

60.0%46.3%62.3%57.9%13.0%53.6%1144elo43.3%4.5%18.7%66.4%65.0%56.8%0.0%100.0%5.0%38.3%62.4%26.7%48.3%0.3592.5%2.61578.1%65.5%60.0%93.0%40.4%023.9%71.9%7.6%29.0%52.9%-0.17100.0%0.0%-332.4%43.0%--98.2%-0.0%28.2%-11.0789.9%-10083.620.790.0%-0.040.0%0.0%1.111.111.01204.5-40.0%41.7%1.4534.5%3.6%17.4%3.3%9.0%80.0%80.0%-83.4%48.6%---100.0%58.2%52.9%0.0%1.5%50.0%--100.0%3.473.471.55-63.3%0.0%0.0%67.5%40.2%-83.5%-6.7%43.8%-------45.4%80.0%-100.0%93.3%100.0%0.0%100.0%-77.9%-0.0%64.0%64.0%20.0%26.7%54.5%-20.0%-20.0%30.0%19.5%96.5%52.0%--30.0%30.0%----0.0%46.8%-40.6%-100.0%88.2%100.0%20.0%-33.3%100.0%73.3%100.0%1.1456.7210.0%----100.0%-100.0%---0.0%100.0%37.6%-1.04100.0%100.0%45.6%93.3%100.0%-90.0%29.0%82.0%82.0%-50.8%
Claude Sonnet 4.5

Anthropic

0.0%37.0%0.0%60.8%0.0%0.0%1675elo0.0%15.2%0.0%72.7%0.0%0.0%0.0%0.0%7.2%42.7%0.0%0.0%59.0%0.750.0%0086.0%64.0%0.0%0.0%42.8%074.8%73.3%28.8%0.0%70.5%---0.0%---1000.0%-0.0%-----5.0%-----------0.0%----------0.0%--0.0%71.40.0%------0.0%83.9%----0.0%-----87.5%-83.8%--70.7%80.4%57.0%53.4%76.5%79.3%77.6%--0.75-----40.6%-84.5%------0.0%-0.0%-----62.9%0.0%--0.0%19.0%0.0%0.0%--0.0%-32.9%----0.0%-------0.0%0.0%77.2%67.0%-0.0%-0050.34---0------22.6%----1.4927.5%
2 / 2 models
AttributeClaude Sonnet 4.5

Anthropic

GPT-4.1 Mini

OpenAI

Descriptionanthropic/claude-sonnet-4.5 is an AI model.GPT-4.1 Mini is an AI model from OpenAI.
FamilyClaudeGPT
ParamsUndisclosed (closed)-
Open weightsclosedclosed
LicenseProprietaryproprietary
Released29 Sep 202514 Apr 2025
Context1,000,0001,047,576
Input $/1M$3.00$0.40
Output $/1M$15.00$1.60
Cache read $/1M$0.300$0.100
Cache write $/1M$3.750-
Speed0 tok/s0 tok/s
Latency0.00 s0.00 s
Modalitiestext, image, fileimage, text, file
Providersanthropic, aws-bedrock, vertex-ai-
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-4.1 Mini better?
Across the 35 benchmarks both models report on Sophon, GPT-4.1 Mini leads on 19 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-4.1 Mini compare on GPQA Diamond?
Claude Sonnet 4.5 scores 72.7% and GPT-4.1 Mini scores 66.4% on GPQA Diamond.
Which is cheaper, Claude Sonnet 4.5 or GPT-4.1 Mini?
GPT-4.1 Mini is cheaper at $1.60 per million output tokens against $15.00 for Claude Sonnet 4.5 - about 9.4x.
When were Claude Sonnet 4.5 and GPT-4.1 Mini released?
Claude Sonnet 4.5 was released 29 Sep 2025 by Anthropic. GPT-4.1 Mini was released 14 Apr 2025 by OpenAI.

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