Reference
Compare models
Select models and benchmarks. Scores are shown exactly within each benchmark’s own metric — never combined into an aggregate, average, or winner.
Models
1 selected
Gemini 3 ProGoogle DeepMind
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
| Benchmark | Gemini 3 ProGoogle DeepMind |
|---|---|
| SWE-bench Verified% resolved | 72.9% |
| GPQA Diamondaccuracy | 92.6% |
SWE-bench Verified
% resolved
Gemini 3 Pro · Google DeepMind
72.9%
GPQA Diamond
accuracy
Gemini 3 Pro · Google DeepMind
92.6%
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.