Skip to content
Model Pareto

Gemini 4 Carbon

Google DeepMindProprietaryblog.google ↗
Compare with nearest rivalsCompare with…
Input
$4.00/M tok
Output
$20/M tok
Blended
$8.00/M tok · 3:1
Speed
83tok/s
Context
1Mtokens

Rankings

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Hard reasoning

GPQA DiamondEstimated
~#2 of 191 (estimated)~95.9%
  1. #1GPT-6 Astra96.1%
  2. ~#2Gemini 4 CarbonEstimated95.9%
  3. #2Gemini 3.8 Flash95.3%
No published score — estimated from related benchmarks
Humanity's Last ExamEstimated
~#2 of 198 (estimated)~61.2%
  1. #1Claude Opus 5.561.4%
  2. ~#2Gemini 4 CarbonEstimated61.2%
  3. #2Claude Fable 5.159.1%
No published score — estimated from related benchmarks
AIME (latest)Estimated
~#2 of 33 (estimated)~98.4%
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Gemini 4 CarbonEstimated98.4%
  3. #2Beam 1.0 501B A23B97.7%
No published score — estimated from related benchmarks