Gemini 2.0 Flash Lite (Preview 02-05) — benchmark results

February 2025 Gemini 2.0 Flash Lite preview snapshot (gemini-2.0-flash-lite-preview-02-05). Provider: Google. Released 2025-02-25. Access: API.

Unified ELO 1534 ± 15, rank #667 of 1776 rated models, from 27 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
KOFFVQA - Korean Recognition60Score (%)76.5
KOFFVQA - Document Understanding80.33Score (%)74.1
KOFFVQA - Table Understanding71.67Score (%)65.4
HELM Capabilities - Omni-MATH37.37Acc62
AA MATH-50087.27Accuracy (%)59.4
KOFFVQA - Recognition75Score (%)58
KOFFVQA - Graph and Chart Understanding63.33Score (%)57.4
KOFFVQA65.24Overall Score (%)53.1
Chatbot Arena (Text)1353Elo52.8
HELM Capabilities - IFEval82.44IFEval Strict Acc52
HELM Capabilities - MMLU-Pro72COT correct52
KOFFVQA - Korean OCR68Score (%)48.1

Interactive version: theaggregate.ai/model?slug=gemini-2-0-flash-lite-preview-02-05 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.