Gemini 3.5 Flash Lite — benchmark results

Provider: Google. Access: API.

Unified ELO 1758 ± 29, rank #182 of 1776 rated models, from 45 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AI Chess Leaderboard (Continuation)1512Elo96.7
AI Chess Leaderboard (Reasoning)1399Elo92.3
AA Omniscience6.92Score92
AA MMMU-Pro79.02Accuracy (%)89.3
Chatbot Arena (Text)1459Elo89
AA Omniscience - Law31.6Accuracy (%)86.9
Artificial Analysis Intelligence Index36.48Intelligence Index85.6
AA GPQA Diamond83.84Accuracy (%)80.3
AA Omniscience - Software Engineering (SWE) - Python39Accuracy (%)80.1
AA Omniscience - Software Engineering (SWE) - C61Accuracy (%)80
AA Omniscience - Business26.5Accuracy (%)79.9
AA-Omniscience Accuracy30.28Accuracy (%)79.9

Interactive version: theaggregate.ai/model?slug=gemini-3-5-flash-lite · How the rankings work · Data refreshed daily, snapshot 2026-07-22.