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

BenchmarkScoreMetricPercentile
Voice Standard v0.1.3 (gpt-5.6-sol; 30s) - Text Correction93Published text_correction task_quality (1-100), canonical v064.5
Chess APO Bench26.3Puzzle accuracy (%) on the 559-puzzle Lichess test split wit62.5
Epoch AI - Mystery Game Puzzles19Score51.4
Epoch AI - GPQA Diamond75.76Accuracy (%)49.1
StudyArena Text - Weighted score1201Weighted score45.5
OTIS Mock AIME 2024-2560Accuracy (%)41.5
Chess Puzzles (Epoch AI)21Accuracy (%)40.8
Voice Standard v0.1.3 (gpt-5.6-sol; 30s) - Dictation98Published dictation task_quality (1-100), canonical v0.1.3, 40.2
Voice Standard v0.1.3 (gpt-5.6-sol; 120s) - Information Extraction85Published information_extraction task_quality (1-100), canon39.4
Voice Standard v0.1.3 (gpt-5.6-sol; 30s) - Summarization96Published summarization task_quality (1-100), canonical v0.139.2
Context Arena40.87Average Score (%)36.7
Voice Standard v0.1.3 (gpt-5.6-sol; 120s) - Summarization93Published summarization task_quality (1-100), canonical v0.133.3

Interactive version: theaggregate.ai/model?slug=gemini-3-5-flash-lite-low · How It Works · Data refreshed daily, snapshot 2026-11-16.