| Benchmark | Claude 3.5 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| AA Intelligence | 10 | 52 |
| Artificial Analysis Coding Index | 30.2 | 69.2 |
| GPQA Diamond | 67.2 | 92.8 |
| HLE | 3.9 | 40.8 |
| MMMU-Pro | 54.7 | 83.2 |
| scicode | 36.6 | 52.7 |
Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.