Gemini 2.5 Flash (Preview 05-20): benchmark results
May 20 Gemini 2.5 Flash preview snapshot. Provider: Google. Released 2025-05-20. Access: API.
Aggregate Rating 1691 ± 13, rank #216 of 1656 rated models, from 145 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Audio - Voxceleb2 | 75.9 | EM | 100 |
| DuckDB-NSQL | 77.3 | Execution Accuracy (%) | 98.4 |
| KOFFVQA - Document Understanding | 100 | Score (%) | 98.1 |
| KOFFVQA - Table Understanding | 96.67 | Score (%) | 98.1 |
| BenchTable - Utility | 82.2 | Weighted Score (%) | 97.4 |
| KOFFVQA - Korean Recognition | 90 | Score (%) | 95.7 |
| KOFFVQA - Commonsense Reasoning | 92 | Score (%) | 95.1 |
| MMMU Benchmark | 79.7 | Validation Score | 94.7 |
| HELM Audio - Air Bench Chat Knowledge | 3.18 | GPT-4o Judge Critique | 93.8 |
| HELM Audio - Air Bench Chat Reasoning | 3.49 | GPT-4o Judge Critique | 93.8 |
| KOFFVQA | 86.76 | Overall Score (%) | 92.6 |
| KOFFVQA - Graph and Chart Understanding | 88 | Score (%) | 92 |
Interactive version: theaggregate.ai/model?slug=gemini-2-5-flash-preview-05-20 · How It Works · Data refreshed daily, snapshot 2026-10-20.