Gemini 1.5 Pro — benchmark results
Google's MoE-based Gemini 1.5 flagship, notable for long-context multimodal understanding of up to 2M tokens (February 2024). Provider: Google. Released 2024-02-15. Access: API.
Unified ELO 1521 ± 6, rank #717 of 1776 rated models, from 599 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AV-Odyssey - Music Score Matching | 29 | Score (%) | 100 |
| AV-Odyssey - Speech Sentiment Analysis | 29.5 | Score (%) | 100 |
| Eval Anything | 4.58 | Overall score | 100 |
| Loong | 55.37 | Overall Avg Score (%) | 100 |
| MMNeedle (1 Image, 8*8 Stitching, Exact Accuracy) | 29.81 | 1 Image, 8*8 Stitching, Exact Accuracy | 100 |
| OpenVLM MMT-Bench - Handwritten Retrieval | 95 | Score (%) | 100 |
| Translation Set1 to en spBleu | 45.6 | Set1âen spBLEU (self-reported) | 100 |
| Vector Eval - IFEval | 89.82 | Final Accuracy (%) | 100 |
| OpenVLM MMT-Bench - Texture Material Recognition | 90 | Score (%) | 99.5 |
| TextClass Benchmark | 1782.7 | Meta-Elo (self-reported) | 99.1 |
| OpenVLM MMT-Bench - 3D CAD Recognition | 80 | Score (%) | 98.5 |
| HELMET (128K) | 64.4 | Average Score | 98.4 |
Interactive version: theaggregate.ai/model?slug=gemini-1-5-pro · How the rankings work · Data refreshed daily, snapshot 2026-07-22.