Gemini 3.1 Flash Lite (Minimal): benchmark results

Provider: Google. Released 2026-05-07. Access: API.

Unified ELO 1641 ± 1, rank #389 of 3078 rated models, from 11 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
SteerBench-Work92.8Mean Trial Accuracy (%)100
SteerBench-Work - Pass^591.5Scenarios Correct in All 5 Trials (%)100
Korean CSAT 2026 (Easy Mode) - English97Points (out of 100)66
Korean CSAT 2026 (Easy Mode) - Korean90.5Points (out of 100)46.9
Korean CSAT 2026 (Easy Mode) - Physics I28Points (out of 50)44.6
FrontierMath - Tiers 1-3 (v2)21.4Accuracy (%, 285 private v2 problems)35.5
Korean CSAT 2026 (Easy Mode) - Total373Points (out of 450)35
Korean CSAT 2026 (Easy Mode) - Chemistry I30Points (out of 50)22.1
Korean CSAT 2026 (Easy Mode) - Life Science I28Points (out of 50)18
Korean CSAT 2026 (Easy Mode) - Mathematics80Points (out of 100)16.3
Korean CSAT 2026 (Easy Mode) - Society and Culture25Points (out of 50)15

Interactive version: theaggregate.ai/model?slug=gemini-3-1-flash-lite-minimal · How It Works · Data refreshed daily, snapshot 2026-09-19.