GoogleAuto-detectedGemini 1.5 Pro 002
Best configuration ranks #452 of 610 on the BenchLeader Index at 42.8 ±4.5. Last measured 2 Sept 2026. Released 24 Sept 2024.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Overall index43
- Reasoning39
- Coding33
- Maths42
- Knowledge36
- Human preference52
- Multimodal48
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 | 57.2%#182 | Epoch AI Benchmarking Hub |
| Humanity's Last Exam | 4.6%#39 | Scale AI / CAIS |
| SimpleBench | 27.1%#69 | SimpleBench |
| LMArena Hard Prompts | 1351#191 | LMArena |
| GPQA Diamond (Vals)not in index | 58.3%#108 | Vals AI |
Coding
| Benchmark | default | Source |
|---|---|---|
| WeirdML | 22.2%#134 | WeirdML |
| LMArena Coding | 1356#215 | LMArena |
| LiveCodeBench | 41.7%#123 | Vals AI |
Maths
| Benchmark | default | Source |
|---|---|---|
| OTIS Mock AIME | 23.1%#198 | Epoch AI Benchmarking Hub |
| MATH Level 5 | 70.4%#37 | Epoch AI Benchmarking Hub |
| AIME (Vals) | 18.8%#79 | Vals AI |
| MGSM | 89.2%#47 | Vals AI |
Knowledge
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1351#179 | LMArena |
Multimodal
| Benchmark | default | Source |
|---|---|---|
| LMArena Vision | 1161#93 | LMArena |
See also
Data as of 9 Sept 2026. Compare with another model.