Gemini 3.5 Flash Lite (Low): benchmark results
Provider: Google. Released 2026-07-21. Access: API.
Aggregate Rating 1652 ± 31, rank #540 of 2245 rated models, from 24 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Voice Standard v0.1.3 (gpt-5.6-sol; 30s) - Text Correction | 93 | Published text_correction task_quality (1-100), canonical v0 | 64.5 |
| Chess APO Bench | 26.3 | Puzzle accuracy (%) on the 559-puzzle Lichess test split wit | 62.5 |
| Epoch AI - Mystery Game Puzzles | 19 | Score | 51.4 |
| Epoch AI - GPQA Diamond | 75.76 | Accuracy (%) | 49.1 |
| StudyArena Text - Weighted score | 1201 | Weighted score | 45.5 |
| OTIS Mock AIME 2024-25 | 60 | Accuracy (%) | 41.5 |
| Chess Puzzles (Epoch AI) | 21 | Accuracy (%) | 40.8 |
| Voice Standard v0.1.3 (gpt-5.6-sol; 30s) - Dictation | 98 | Published dictation task_quality (1-100), canonical v0.1.3, | 40.2 |
| Voice Standard v0.1.3 (gpt-5.6-sol; 120s) - Information Extraction | 85 | Published information_extraction task_quality (1-100), canon | 39.4 |
| Voice Standard v0.1.3 (gpt-5.6-sol; 30s) - Summarization | 96 | Published summarization task_quality (1-100), canonical v0.1 | 39.2 |
| Context Arena | 40.87 | Average Score (%) | 36.7 |
| Voice Standard v0.1.3 (gpt-5.6-sol; 120s) - Summarization | 93 | Published summarization task_quality (1-100), canonical v0.1 | 33.3 |
Interactive version: theaggregate.ai/model?slug=gemini-3-5-flash-lite-low · How It Works · Data refreshed daily, snapshot 2026-11-16.