Skip to content
English

Switch theme

Google

Gemini 1.5 Flash (Sep 2024) benchmark results

9 results on 8 benchmarks from 4 sources.

Closed Released: Sep 24, 2024 Updated Oct 22, 2026

Also listed as: gemini-1.5-flash-002 · Gemini 1.5 Flash (002) · Gemini 1.5 Flash 002 · Gemini-1.5-Flash-002

All benchmark results

Benchmarks Score Rank Setting Source type Date
LMArena Text 1309 273 Overall, style control on; 34902 votes; 95% CI 1305–1314“gemini-1.5-flash-002” Official leaderboard Oct 8, 2026
LMArena Vision 1141 116 Overall, style control on; 7241 votes; 95% CI 1132–1151“gemini-1.5-flash-002” Official leaderboard Oct 2, 2026
GPQA Diamond 47.3% 218 Epoch AI run, accuracy Independent run Jan 27, 2025
MMLU 73.9% 43 Exact match; 5-shot Official leaderboard via Epoch AI Sep 24, 2024
MMLU-Pro 64.1% 122 Overall accuracy; data source: TIGER-Lab“Gemini-1.5-Flash-002” Official leaderboard Mar 11, 2026
HumanEval / HumanEval+ 82.3% 17 HumanEval (base tests), pass@1 greedy“Gemini 1.5 Flash 002” Official leaderboard Dec 26, 2024
HumanEval / HumanEval+ 75.6% 18 HumanEval+ (extended tests), pass@1 greedy“Gemini 1.5 Flash 002” Official leaderboard Dec 26, 2024
AIME (OTIS Mock AIME 2024–2025) 16.3% 210 Epoch AI run, OTIS Mock AIME 2024–2025 Independent run Feb 25, 2025
MATH Level 5 61.9% 52 Epoch AI run, accuracy Independent run Jan 27, 2025
← AI Model Benchmarks

FAQ

Where do these Gemini 1.5 Flash (Sep 2024) scores come from?

From Epoch AI Benchmarking Hub, EvalPlus leaderboard, LMArena leaderboard dataset, and MMLU-Pro leaderboard (TIGER-Lab). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.

Data updated: Benchmarks(UTC+8)