OmniGameArena - SharedFloor — leaderboard
Metric: Normalized game score (%). Source: arxiv.org. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 36.8 |
| 2 | Gemini 3.1 Pro (Preview) | 33.6 |
| 3 | Claude Opus 4.6 | 15.2 |
| 4 | Claude Sonnet 4.6 | 14.8 |
| 5 | Claude Opus 4.7 | 13.6 |
| 6 | Kimi K2.5 | 7.2 |
| 7 | GPT-5.4 | 6.8 |
| 8 | Gemini 3.1 Flash Lite (Preview) | 5.2 |
| 9 | Qwen 3.5 122B A10B | 0.8 |
| 10 | Qwen 3.5 397B A17B | 0 |
Interactive version: aibenchmarks.dev/benchmark?slug=omnigamearena-sharedfloor · How the rankings work · Data refreshed daily, snapshot 2026-07-06.