GoogleAuto-detectedGemini 1.5 Pro
Best configuration ranks #451 of 610 on the BenchLeader Index at 42.9 ±4.0. Last measured 5 Mar 2025stale: no new result in six months.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 2M
- Overall index43
- Reasoning35
- Multimodal42
- Composite39
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 58.9%#363 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 4.6%#404 | Artificial Analysis |
| ARC-AGI-2 | 0.8%#164 | ARC Prize |
Multimodal
| Benchmark | default | Source |
|---|---|---|
| MMMU-Pro | 55.0%#195 | Artificial Analysis |
| VISTA | 37.1%#43 | Scale AI SEAL |
| MMMU (validation) | 65.8%#26 | MMMU |
| MMMU-Pro (official)not in index | 46.9%#17 | MMMU |
Composite
| Benchmark | default | Source |
|---|---|---|
| Epoch Capabilities Indexnot in index | 131.7#128 | Epoch AI Benchmarking Hub |
| AA Intelligence Index | 7.9#372 | Artificial Analysis |
See also
Data as of 9 Sept 2026. Compare with another model.