Gemini 1.5 Pro (Preview 0409): benchmark results
Provider: Google. Access: API.
Aggregate Rating 1603 ± 21, rank #978 of 10916 rated models, from 222 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM VHELM - Image2Webpage | 67.54 | EMD-Sim | 100 |
| Open Portuguese LLM - OAB Exams | 68.88 | Accuracy (%) | 98.1 |
| Open Portuguese LLM - ENEM | 85.09 | Accuracy (%) | 98 |
| HELM MMLU - College Physics | 80.39 | EM | 97.4 |
| Open Portuguese LLM - BLUEX | 77.19 | Accuracy (%) | 96.7 |
| HELM MMLU - Conceptual Physics | 91.49 | EM | 94.9 |
| HELM VHELM - Blink Perception - Spatial Relation | 98.6 | Prefix Quasi-Exact Match (%) | 94.7 |
| HELM VHELM - Seed Bench - Visual Reasoning | 83.69 | Prefix Quasi-Exact Match (%) | 94.7 |
| HELM MMLU - Elementary Mathematics | 88.36 | EM | 93.6 |
| HELM VHELM - Bias | 93.62 | Mean win rate | 93.6 |
| HELM VHELM - Pairs | 92.34 | PEM | 93.6 |
| HELM MMLU - Econometrics | 73.68 | EM | 92.9 |
Interactive version: theaggregate.ai/model?slug=gemini-1-5-pro-preview-0409 · How It Works · Data refreshed daily, snapshot 2026-11-08.