Google: gemini-3.6-flash
2 benchmarks
Leaderboard position
#74
Overall rank (of 1121 models)
2411
Elo rating
2
Benchmarks
Top 6.6%
Percentile
In Google (of 72 models)
Above: Ornith: ornith-1.0-397b #73
Below: infly: infinity-parser2-pro #75
Benchmark highlights
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 2 of 2 benchmarks
2/2
100.0%
Benchmarks
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.
| Benchmark | Predicted | Confidence | Based on |
|---|---|---|---|
| MATH-500 | ~99.2 | 50% | — |
| AIME 2025 | ~100 | 50% | — |
| AIME 2026 | ~99.2 | 50% | — |
| HMMT Feb 2026 | ~95.22 | 50% | — |
| GPQA Diamond | ~92.33 | 50% | — |
| MMLU-Pro | ~90.53 | 50% | — |
| Humanity's Last Exam (no tools) | ~39.33 | 50% | — |
| IFEval | ~96.75 | 50% | — |
| IFBench | ~79.1 | 50% | — |
| HumanEval | ~95.9 | 50% | — |
| MBPP | ~93.7 | 50% | — |
| Terminal-Bench v2.1 | ~75.46 | 50% | — |
| MMLU | ~92.5 | 50% | — |
| SWE-bench Verified | ~88.03 | 50% | — |
| SWE-bench Pro | ~63.68 | 50% | — |
| SciCode | ~51.24 | 50% | — |
| AA-LCR | ~73.51 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~27.7 | 50% | — |
| Humanity's Last Exam (with tools) | ~52.85 | 50% | — |
| GSM8K | ~99.6 | 50% | — |
| -(CoderPPL) | ~-1.69 | 50% | — |
| LiveCodeBench v6 | ~90.33 | 50% | — |
| MMMU-Pro | ~82.18 | 50% | — |
| MATH | ~97.9 | 50% | — |
| BBH | ~88.4 | 50% | — |