0

Claude 4 Sonnet vs Gemini 2.5 Pro

Head to head on 25 shared benchmarks, with price, context window, and release dates.

Benchmark scores

48

evals · sort by any column, ⤢ to expand fullscreen

Model
Gemini 2.5 Pro

Google (Alphabet Inc.)

88.7%87.7%60.8%45.2%1419elo58.884.4%22.5%48.7%77.9%86.7%81.0%65.9%80.1%96.7%50.6%73.6%86.2%68.9%41.9%42.8%53.6%72.9%26.5%54.1%83.1%50.4%--15.9%14.1%-----70.0%---55.6---0.4%--53.3%59.5%
Claude 4 Sonnet

Anthropic

40.7%38.0%54.7%19.8%1480elo58.468.3%4.3%45.4%64.8%77.5%44.3%72.9%44.9%93.4%33.9%72.4%83.7%62.5%35.0%37.3%74.6%69.6%27.3%52.3%--22.9%47.8%--67.5%54.6%70.5%69.0%86.7%-43.9%6.186.18-58.3%35.6%0.59-84.0%84.0%-55.5%
2 / 2 models
AttributeClaude 4 Sonnet

Anthropic

Gemini 2.5 Pro

Google (Alphabet Inc.)

DescriptionClaude 4 Sonnet is an AI model from Anthropic.Gemini 2.5 Pro is an AI model from Google (Alphabet Inc.).
FamilyClaudeGemini
Params--
Open weightsclosedclosed
Licenseproprietaryproprietary
Released22 May 20255 Jun 2025
Context200,0001,048,576
Input $/1M$3.00$1.25
Output $/1M$15.00$10.00
Cache read $/1M-$0.125
Cache write $/1M-$0.375
Speed0 tok/s0 tok/s
Latency0.00 s0.00 s
Modalitiestext, imagetext, image, file, audio, video
Providers--
PublisherAnthropicGoogle (Alphabet Inc.)
Reported scores

FAQ

Is Claude 4 Sonnet or Gemini 2.5 Pro better?
Across the 25 benchmarks both models report on Sophon, Gemini 2.5 Pro leads on 21 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
How do Claude 4 Sonnet and Gemini 2.5 Pro compare on GPQA Diamond?
Claude 4 Sonnet scores 68.3% and Gemini 2.5 Pro scores 84.4% on GPQA Diamond.
Which is cheaper, Claude 4 Sonnet or Gemini 2.5 Pro?
Gemini 2.5 Pro is cheaper at $10.00 per million output tokens against $15.00 for Claude 4 Sonnet - about 1.5x.
When were Claude 4 Sonnet and Gemini 2.5 Pro released?
Claude 4 Sonnet was released 22 May 2025 by Anthropic. Gemini 2.5 Pro was released 5 Jun 2025 by Google (Alphabet Inc.).

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