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 3.1 Pro PreviewGoogle DeepMind
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
| Benchmark | Gemini 3.1 Pro PreviewGoogle DeepMind |
|---|---|
| SWE-bench Verified% resolved | 75.6% |
| GPQA Diamondaccuracy | 94.1% |
SWE-bench Verified
% resolved
Gemini 3.1 Pro Preview · Google DeepMind
75.6%
GPQA Diamond
accuracy
Gemini 3.1 Pro Preview · Google DeepMind
94.1%
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.