GoogleAuto-detectedGemini 1.5 Flash 002
Best configuration ranks #543 of 610 on the BenchLeader Index at 38.7 ±5.4. Last measured 2 Sept 2026. Released 24 Sept 2024.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Overall index39
- Reasoning39
- Coding30
- Maths39
- Knowledge22
- Human preference47
- Multimodal42
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 | 47.3%#211 | Epoch AI Benchmarking Hub |
| LMArena Hard Prompts | 1303#234 | LMArena |
| GPQA Diamond (Vals)not in index | 46.0%#121 | Vals AI |
Coding
| Benchmark | default | Source |
|---|---|---|
| WeirdML | 24.9%#131 | WeirdML |
| LMArena Coding | 1316#240 | LMArena |
| LiveCodeBench | 36.9%#127 | Vals AI |
Maths
| Benchmark | default | Source |
|---|---|---|
| OTIS Mock AIME | 16.3%#206 | Epoch AI Benchmarking Hub |
| MATH Level 5 | 61.9%#46 | Epoch AI Benchmarking Hub |
| AIME (Vals) | 17.3%#80 | Vals AI |
| MGSM | 86.6%#59 | Vals AI |
Knowledge
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1309#224 | LMArena |
Multimodal
| Benchmark | default | Source |
|---|---|---|
| LMArena Vision | 1141#101 | LMArena |
| VISTA | 34.0%#46 | Scale AI SEAL |
See also
Data as of 9 Sept 2026. Compare with another model.