GoogleAuto-detectedGemini 2.0 Pro
Best configuration ranks #359 of 610 on the BenchLeader Index at 47.0 ±6.8. Last measured 1 Sept 2026. Released 5 Feb 2025.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 2M
- Overall index47
- Reasoning49
- Coding43
- Maths62
- Knowledge37
- Multimodal54
- Long context37
- Composite40
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 | 65.7%#167 | Epoch AI Benchmarking Hub |
| GPQA Diamond (AA)not in index | 62.2%#344 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 6.2%#330 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| Aider Polyglot | 35.6%#30 | Aider polyglot leaderboard |
Maths
| Benchmark | default | Source |
|---|---|---|
| MATH Level 5 | 83.5%#29 | Epoch AI Benchmarking Hub |
Multimodal
| Benchmark | default | Source |
|---|---|---|
| VISTA | 43.3%#33 | Scale AI SEAL |
| MMMU (validation) | 72.7%#19 | MMMU |
Long context
| Benchmark | default | Source |
|---|---|---|
| Fiction.LiveBench 120k | 37.5%#26 | Fiction.live |
Composite
| Benchmark | default | Source |
|---|---|---|
| Epoch Capabilities Indexnot in index | 135.1#118 | Epoch AI Benchmarking Hub |
| AA Intelligence Index | 8.8#352 | Artificial Analysis |
See also
Data as of 9 Sept 2026. Compare with another model.