| Benchmark | Gemini 1.5 Pro | Qwen3.5 397B A17B |
|---|---|---|
| AA Intelligence | 10 | 34.3 |
| arena_vision | 1179 | 1249 |
| Artificial Analysis Coding Index | 23.6 | 48.2 |
| GPQA Diamond | 59.1 | 89.3 |
| GSM8K | 95.2 | 66.7 |
| HLE | 4.9 | 29 |
| ifeval | 89.4 | 92.6 |
| MMLU-Pro | 75.8 | 87.8 |
| MMMU | 68.4 | 85 |
| MMMU-Pro | 55 | 79 |
| scicode | 29.5 | 42 |
| SWE-bench Verified | 34.2 | 76.4 |
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.