Skip to content
English

Switch theme

Google

Gemini 4 Argon benchmark results

6 results on 5 benchmarks from 3 sources.

Closed Released: Sep 30, 2026 Updated Oct 22, 2026

Also listed as: gemini-4-argon_high · Gemini 4 Argon (high) · Gemini 4 Argon (High) · Gemini 4 Argon (Medium)

All benchmark results

Benchmarks Score Rank Setting Source type Date
LMArena Text 1525 1 Overall, style control on; 4892 votes; 95% CI 1517–1534“gemini-4-argon-high” Official leaderboard Oct 8, 2026
LMArena WebDev 1678 9 Overall; 1771 votes; 95% CI 1662–1693“gemini-4-argon-high” Official leaderboard Oct 8, 2026
GPQA Diamond 96.4% 1 Epoch AI run, accuracy; effort: high Independent run Oct 13, 2026
AIME (OTIS Mock AIME 2024–2025) 100.0% 1 Epoch AI run, OTIS Mock AIME 2024–2025; effort: high Independent run Oct 13, 2026
ARC-AGI-1 98.5% 9 Semi-private set; $0.16/task; CoT“Gemini 4 Argon (High)” Official leaderboard Oct 22, 2026
ARC-AGI-1 98.5% 10 Semi-private set; $0.06/task; CoT“Gemini 4 Argon (Medium)” Official leaderboard Oct 22, 2026
← AI Model Benchmarks

FAQ

Where do these Gemini 4 Argon scores come from?

From Epoch AI Benchmarking Hub, ARC Prize leaderboard, and LMArena leaderboard dataset. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.

Data updated: Benchmarks(UTC+8)