Gemini 1.5 Flash — benchmark results
Google's lightweight, fast Gemini 1.5 tier distilled from 1.5 Pro, with a 1M-token multimodal context (May 2024). Provider: Google. Released 2024-05-15. Access: API.
Unified ELO 1486 ± 6, rank #855 of 1776 rated models, from 567 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AudioBench - YouTube ASR Batch 1 WER | 10.89 | WER (%) (lower is better) | 100 |
| AudioBench - YouTube SDS | 65.97 | Mean Score (%) | 100 |
| AudioBench - YouTube SQA | 78.07 | Mean Score (%) | 100 |
| Galileo Tool Tasks - ToolACE Single Function Call | 99 | Accuracy (%) | 100 |
| RABBITS MedQA Original | 97.09 | Accuracy (%) | 100 |
| OpenVLM MMT-Bench - 3D | 65 | Score (%) | 99.8 |
| OpenVLM MMT-Bench - 3D CAD Recognition | 85 | Score (%) | 99.8 |
| OpenVLM MMT-Bench - Facial Expression Change Recognition | 100 | Score (%) | 99.5 |
| OpenVLM MMT-Bench - Texture Material Recognition | 90 | Score (%) | 99.5 |
| OpenVLM MMT-Bench - Celebrity Recognition | 100 | Score (%) | 99.3 |
| OpenVLM MMMU - Literature | 93.3 | Accuracy (%) | 98.1 |
| OpenVLM MMT-Bench - DocVQA | 90 | Score (%) | 98.1 |
Interactive version: theaggregate.ai/model?slug=gemini-1-5-flash · How the rankings work · Data refreshed daily, snapshot 2026-07-22.