Gemini-2.5 Flash-Lite Preview: benchmark results
Provider: Google. Released 2025-06-17. Access: API.
Aggregate Rating 1590 ± 30, rank #1117 of 10916 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI for Education Visual Reasoning - odd one out | 50.6 | Accuracy (%) | 53.8 |
| AI for Education SEND | 73.39 | Accuracy (%) | 49.4 |
| AI for Education Pedagogy - Primary | 81.69 | Accuracy (%) | 46.1 |
| AI for Education Pedagogy - Social studies | 75.45 | Accuracy (%) | 45.9 |
| AI for Education Pedagogy - Secondary | 75.31 | Accuracy (%) | 45.1 |
| AI for Education Pedagogy | 76.2 | Accuracy (%) | 44.3 |
| AI for Education Visual Maths - Number and Operations | 45.95 | Accuracy (%) | 41.9 |
| AI for Education Pedagogy - Maths | 73.81 | Accuracy (%) | 41.4 |
| AI for Education Visual Maths - Geometry | 43.08 | Accuracy (%) | 39.9 |
| AI for Education Visual Maths - Measurement | 64.86 | Accuracy (%) | 39.9 |
| AI for Education Visual Reasoning - reasoning by analogy | 36.3 | Accuracy (%) | 39.2 |
| AI for Education Visual Reasoning - pattern completion (2d) | 38.4 | Accuracy (%) | 38.5 |
Interactive version: theaggregate.ai/model?slug=gemini-2-5-flash-lite-preview · How It Works · Data refreshed daily, snapshot 2026-11-08.