OmniGameArena - SoloCraft: leaderboard

The "SoloCraft" subtask of OmniGameArena. OmniGameArena (arXiv) — Unreal-Engine-5 game environments testing vision-language agents on real-time perception, control and planning across solo and co-op games; normalized game score (%).

Metric: Normalized game score (%). Source: arxiv.org. Saturation forecast: Around June 2027. 12 models tracked.

Top models

#ModelScoreOverall rank
1GPT-5.525.2#31
2Claude Opus 4.622.8#63
3Claude Opus 4.716#49
4Gemini 3.1 Pro (Preview)14.8#58
5Claude Sonnet 4.612.4#90
6GPT-5.48.4#79
7Kimi K2.56.4#144
8Gemini 3.1 Flash Lite (Preview)3.6#194
9Qwen 3.5 122B A10B1.3#173
10Qwen 3.5 397B A17B0#146

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=omnigamearena-solocraft · How It Works · Data refreshed daily, snapshot 2026-10-20.