Skip to content
English

Switch theme

Google

Gemini 3 Flash benchmark results

18 results on 8 benchmarks from 4 sources.

Closed Released: Dec 17, 2025 Updated Oct 22, 2026 API prices & specs →

Also listed as: gemini-3-flash · gemini-3-flash (thinking-minimal) · gemini-3-flash-preview_high · Gemini 3 Flash Preview · gemini-3-flash-preview · Gemini 3 Flash (high)

All benchmark results

Benchmarks Score Rank Setting Source type Date
LMArena Text 1473 43 Overall, style control on; 31337 votes; 95% CI 1469–1477“gemini-3-flash” Official leaderboard Oct 8, 2026
LMArena Text 1458 61 Overall, style control on; 91105 votes; 95% CI 1455–1461“gemini-3-flash (thinking-minimal)” Official leaderboard Oct 8, 2026
LMArena WebDev 1439 75 Overall; 10894 votes; 95% CI 1431–1448“gemini-3-flash” Official leaderboard Oct 8, 2026
LMArena WebDev 1385 97 Overall; 22176 votes; 95% CI 1379–1390“gemini-3-flash (thinking-minimal)” Official leaderboard Oct 8, 2026
LMArena Vision 1273 34 Overall, style control on; 39142 votes; 95% CI 1268–1278“gemini-3-flash” Official leaderboard Oct 2, 2026
LMArena Vision 1260 43 Overall, style control on; 37184 votes; 95% CI 1254–1265“gemini-3-flash (thinking-minimal)” Official leaderboard Oct 2, 2026
GPQA Diamond 89.4% 49 Epoch AI run, accuracy Independent run Aug 6, 2026
SWE-bench Verified 75.4% 13 Epoch AI run (Epoch scaffold) Independent run Feb 18, 2026
SWE-bench Verified 75.8% 6 agent: mini-SWE-agent“gemini-3-flash-preview” Official leaderboard Feb 17, 2026
AIME (OTIS Mock AIME 2024–2025) 95.6% 43 Epoch AI run, OTIS Mock AIME 2024–2025 Independent run Aug 6, 2026
τ²-bench 82.5% 3 airline domain, pass^1; effort: high; submitted by Sierra; v1.0.1 Official leaderboard Mar 2, 2026
τ²-bench 27.3% 15 banking_knowledge domain, pass^1; effort: high; submitted by Sierra; v1.0.1 Official leaderboard Mar 2, 2026
τ²-bench 76.8% 14 retail domain, pass^1; effort: high; submitted by Sierra; v1.0.1 Official leaderboard Mar 2, 2026
τ²-bench 91.2% 9 telecom domain, pass^1; effort: high; submitted by Sierra; v1.0.1 Official leaderboard Mar 2, 2026
Terminal-Bench 2.0 64.3% 36 Terminal-Bench 2.0; agent: Junie CLI Official leaderboard via Epoch AI Dec 17, 2025
Terminal-Bench 2.0 51.7% 67 Terminal-Bench 2.0; agent: Terminus 2 Official leaderboard via Epoch AI Dec 17, 2025
Terminal-Bench 2.0 51.0% 69 Terminal-Bench 2.0; agent: Gemini CLI Official leaderboard via Epoch AI Dec 23, 2025
Terminal-Bench 2.0 47.4% 75 Terminal-Bench 2.0; agent: Gemini CLI Official leaderboard via Epoch AI Dec 17, 2025

Related on this site

← AI Model Benchmarks

FAQ

Where do these Gemini 3 Flash scores come from?

From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, SWE-bench leaderboards (swebench.com), and τ²-bench leaderboard submissions. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.

Data updated: Benchmarks(UTC+8)