LMArcade - aq-gaming: leaderboard

LMArcade head-to-head human-voted playable-game Elo leaderboard inside the aq-gaming coding-agent harness (builds >= 5).

Metric: Elo Rating. Source: www.lmarcade.com. Saturation forecast: Around September 2027. 26 models tracked. Updated 22 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Opus 4.71753#86
2GPT-5.5Medium1752#56
3Claude Fable 51724#32
4Claude Opus 4.81678#64
5Claude Opus 51676#26
6MiMo-V2.5-Pro1657#292
7Qwen 3.6 Max1652#192
8Claude Sonnet 51644#124
9Claude Sonnet 4.61636#179
10GPT-5.4Medium1599#138
11DeepSeek V4 Flash1597#273
12GLM-5.11557#200
13Kimi K31555#62
14MiniMax-M31535#290
15DeepSeek V4 Pro1534#201

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=lmarcade-aq-gaming · How It Works · Data refreshed daily, snapshot 2026-11-22.