Gemini 1.5 Flash (002) — benchmark results

Gemini 1.5 Flash 002 stable API snapshot. Provider: Google. Released 2024-09-24. Access: API.

Unified ELO 1570 ± 5, rank #565 of 1776 rated models, from 840 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MEGA-Bench Task - NLVR2 Two Image Compare QA85.7Task Score (%)98.8
MEGA-Bench Task - Video Content Reasoning88.9Task Score (%)98.8
MEGA-Bench Task - Webpage Code Understanding88.9Task Score (%)98.8
OpenVLM MMBench V1.1 CN - Identity Reasoning100Accuracy (%)97.9
MEGA-Bench Task - Electricity Plot Future Prediction90.2Task Score (%)97.7
MEGA-Bench Task - LLaVAGuard78.6Task Score (%)97.7
MEGA-Bench Task - Medical Retrieval Given Surgeon Activity57.1Task Score (%)97.7
MEGA-Bench Task - Video Camera Motion Description35.7Task Score (%)97.7
MEGA-Bench Task - MMSoc Misinformation GossipCop78.6Task Score (%)96.5
MEGA-Bench Task - Multi Load Type Prediction From Plot53.6Task Score (%)96.5
OpenVLM MMMU - History83.3Accuracy (%)96.5
OpenVLM MMBench V1.1 EN - Function Reasoning96.7Accuracy (%)96.3

Interactive version: theaggregate.ai/model?slug=gemini-1-5-flash-002 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.