Elimination Game (Lechmazur) — leaderboard

20 Questions-style elimination game where models must identify a target from a large set using yes/no questions. TrueSkill ranking from multi-game tournaments across 60+ models.

Metric: TrueSkill μ. Source: github.com. Status: saturation imminent. 61 models tracked.

Top models

#ModelScore
1GPT-5.2 (Medium)7.52
2GPT-5 (Medium)5.97
3GPT-5 Mini (Medium)5.73
4Gemini 3 Flash (Preview)5.66
5GPT-4o (Mar 2025)5.5
6DeepSeek R1 05285.35
7Claude Opus 4.1 (Non-reasoning)5.21
8Claude Sonnet 4.5 (Thinking 16K)5.19
9Grok 45.15
10GPT-4.5 (Preview)5.12
11Claude 3.5 Sonnet (20241022)5.1
12Grok 35.1
13Gemini 3 Pro (Preview)4.89
14Claude 3.7 Sonnet4.78
15Gemini 2.5 Flash4.73

Interactive version: theaggregate.ai/benchmark?slug=elimination-game-lechmazur · How the rankings work · Data refreshed daily, snapshot 2026-07-22.