LLM Live - Chess - Glicko-2 Rating: leaderboard
LLM Live's chess arena ratings under a fixed 1,024-reasoning-token cap per move. Glicko-2 ratings are unbounded, with native uncertainty and sample counts retained. A third illegal move or three no-move replies forfeits; provider API-error games are unrated. Exact provider-route links identify evaluated systems without inventing dated endpoints or full-effort settings. The source conservatively orders by rating minus two deviations; the metric here is its native point rating.
Metric: Glicko-2 chess rating (unbounded; 1024 reasoning-token cap). Source: llmlive.ai. Saturation forecast: Rough model projection: around 2026. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.7 Flash (LLM Live Run: chess;reasoning-cap=1024;provider-route=google/gemini-3.7-flash) | 2232 | |
| 2 | Grok 4.3 (LLM Live Run: chess;reasoning-cap=1024;provider-route=x-ai/grok-4.3) | 1697 | |
| 3 | Claude Haiku 5.5 (LLM Live Run: chess;reasoning-cap=1024;provider-route=anthropic/claude-haiku-5.5) | 1649 | |
| 4 | GPT-6 Luna (LLM Live Run: chess;reasoning-cap=1024;provider-route=openai/gpt-6-luna) | 1643 | |
| 5 | Qwen 3.8 Flash (LLM Live Run: chess;reasoning-cap=1024;provider-route=qwen/qwen3.8-flash) | 1505 | |
| 6 | DeepSeek V4.1 Flash (LLM Live Run: chess;reasoning-cap=1024;provider-route=deepseek/deepseek-v4.1-flash) | 1436 | |
| 7 | GLM-5.3 Flash (LLM Live Run: chess;reasoning-cap=1024;provider-route=z-ai/glm-5.3-flash) | 1429 | |
| 8 | Kimi K2.6 (LLM Live Run: chess;reasoning-cap=1024;provider-route=moonshotai/kimi-k2.6) | 1338 | |
| 9 | Mistral Small 4 (LLM Live Run: chess;reasoning-cap=1024;provider-route=mistralai/mistral-small-2603) | 1276 | |
| 10 | MiniMax-M3.1-Flash (LLM Live Run: chess;reasoning-cap=1024;provider-route=minimax/minimax-m3.1-flash) | 916 |
Interactive version: theaggregate.ai/benchmark?slug=llm-live-chess-glicko-2-rating · How It Works · Data refreshed daily, snapshot 2026-11-05.