Gemini 1.5 Flash (Preview 0514): benchmark results
Provider: Google. Access: API.
Aggregate Rating 1587 ± 21, rank #1154 of 10916 rated models, from 208 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM VHELM - Mmmu - History | 90 | Prefix Quasi-Exact Match (%) | 97.9 |
| Open Portuguese LLM - OAB Exams | 64.19 | Accuracy (%) | 96.5 |
| Open Portuguese LLM - ENEM | 82.65 | Accuracy (%) | 96 |
| Open Portuguese LLM - BLUEX | 74.83 | Accuracy (%) | 95.4 |
| HELM VHELM - Blink Reasoning - IQ Test | 50.67 | Prefix Quasi-Exact Match (%) | 93.6 |
| HELM VHELM - Blink Reasoning | 80.89 | PEM | 92.6 |
| HELM MMLU - Electrical Engineering | 81.38 | EM | 91.7 |
| Open Portuguese LLM - FaQuAD NLI | 80.92 | Macro F1 (%) | 91.2 |
| Open Portuguese LLM - ASSIN2 RTE | 93.62 | Macro F1 (%) | 90.6 |
| HELM VHELM - Blink Reasoning - Multi-view Reasoning | 100 | Prefix Quasi-Exact Match (%) | 90.4 |
| Open Portuguese LLM - ASSIN2 STS | 84.17 | Pearson Correlation (×100) | 90.2 |
| HELM VHELM - Pope | 88.9 | PEM | 86.2 |
Interactive version: theaggregate.ai/model?slug=gemini-1-5-flash-preview-0514 · How It Works · Data refreshed daily, snapshot 2026-11-08.