| Benchmark | Gemini 3.6 Flash | Gemma 4 E2B |
|---|---|---|
| AA Agentic Index | 40.5 | 7.4 |
| AA Intelligence | 52 | 10 |
| AA-LCR | 79 | 17 |
| AA-Omniscience | 22.1 | -23.6 |
| aime_2026 | 96.7 | 37.5 |
| Artificial Analysis Coding Index | 69.2 | 8.3 |
| critpt | 10.6 | 0 |
| gdpval | 46.1 | 0 |
| GPQA Diamond | 92.8 | 43.4 |
| HLE | 40.8 | 4.8 |
| MMMU-Pro | 83.2 | 44.6 |
| mrcr_v2_8needle_128k_average | 91.8 | 19.1 |
| OmniScience Accuracy | 50 | 8.2 |
| OmniScience Non-Hallucination | 44.4 | 67.6 |
| scicode | 52.7 | 20.9 |
| TauBench V3 - Banking | 29.9 | 4.5 |
| Terminal-Bench 2.1 | 78 | 0.4 |
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.