| Benchmark | Gemini 3.6 Flash | o1 |
|---|---|---|
| AA Agentic Index | 40.5 | 31.1 |
| AA Intelligence | 52 | 24 |
| AA-LCR | 79 | 63.3 |
| AA-Omniscience | 22.1 | -10.6 |
| Artificial Analysis Coding Index | 69.2 | 39.7 |
| critpt | 10.6 | 0.3 |
| gdpval | 46.1 | 11.5 |
| GPQA Diamond | 92.8 | 75.7 |
| HLE | 40.8 | 7.7 |
| OmniScience Accuracy | 50 | 34.7 |
| OmniScience Non-Hallucination | 44.4 | 30.7 |
| scicode | 52.7 | 35.8 |
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.