Skip to content

LLM Benchmark Hub

Model evidence, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Metrics
LLM Benchmark Hub
Loading data...

OmniGameArena - SceneEscape — leaderboard

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

Top models

#ModelScore
1GPT-5.572
2GPT-5.468
3Gemini 3.1 Pro (Preview)66
4Claude Opus 4.654
5Claude Opus 4.746
6Claude Sonnet 4.644
7Gemini 3.1 Flash Lite (Preview)30
8Kimi K2.522
9Qwen 3.5 397B A17B20
10Qwen 3.5 122B A10B6

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