| Benchmark | Gemini 1.5 Pro | Qwen3.6 Plus |
|---|---|---|
| AA Intelligence | 10 | 40.5 |
| AI2D | 80.9 | 94.4 |
| Artificial Analysis Coding Index | 23.6 | 54.5 |
| GPQA Diamond | 59.1 | 90.4 |
| HLE | 4.9 | 28.8 |
| ifeval | 89.4 | 94.3 |
| MMLU-Pro | 75.8 | 88.5 |
| MMMU | 68.4 | 86 |
| MMMU-Pro | 55 | 78.8 |
| scicode | 29.5 | 40.7 |
| SWE-bench Verified | 34.2 | 78.8 |
| Video-MME | 78.6 | 84.2 |
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.