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 2.5 ProGoogle DeepMind
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
| Benchmark | Gemini 2.5 ProGoogle DeepMind |
|---|---|
| SWE-bench Verified% resolved | 57.6% |
| GPQA Diamondaccuracy | 85.3% |
SWE-bench Verified
% resolved
Gemini 2.5 Pro · Google DeepMind
57.6%
GPQA Diamond
accuracy
Gemini 2.5 Pro · Google DeepMind
85.3%
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.