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 - CueChase — leaderboard

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

Top models

#ModelScore
1Claude Opus 4.684
2Gemini 3.1 Pro (Preview)60
3GPT-5.558
4Claude Sonnet 4.644
5Gemini 3.1 Flash Lite (Preview)44
6Claude Opus 4.738
7GPT-5.430
8Kimi K2.514
9Qwen 3.5 397B A17B4
10Qwen 3.5 122B A10B4

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