OmniGameArena - LastStand — leaderboard

Metric: Normalized game score (%). Source: arxiv.org. 10 models tracked.

Top models

#ModelScore
1GPT-5.541.6
2Claude Opus 4.730.8
3Kimi K2.523.2
4Gemini 3.1 Pro (Preview)23
5GPT-5.414.8
6Claude Opus 4.614.7
7Claude Sonnet 4.614.4
8Gemini 3.1 Flash Lite (Preview)12.2
9Qwen 3.5 397B A17B10.6
10Qwen 3.5 122B A10B9.3

Interactive version: aibenchmarks.dev/benchmark?slug=omnigamearena-laststand · How the rankings work · Data refreshed daily, snapshot 2026-07-06.