Per-game leaderboard

Game 02

This page shows the per-game leaderboard for Game 02 in the highest reasoning. Entries are ranked by their normalized score within this game.

Game 02 leaderboard

Entries ranked by normalized score. Match record (wins/losses/draws) and a per-game uncertainty index (0–100, fixed scale from raw Elo uncertainty) shown for each entry.

Reasoning level: Highest Game: Game 02 Build: Preview
Game 02 — Highest reasoning
# Entry Score W / L / D Uncertainty
1Claude Sonnet 4.6100.055/16/1011.5
2Qwen3 Max Thinking98.060/11/1011.5
3Kimi K2.597.453/12/1810.8
4GPT-5.4 Nano96.340/6/3615.7
5GPT-5 Mini93.749/17/1511.5
6Minimax M2.590.156/16/1210.5
7Gemini 2.5 Flash77.930/12/2516.9
8MiMo-V2-Pro74.024/12/5013.8
9Mistral Small 260368.733/19/1118.8
10GPT-5 Nano68.236/29/1810.8
11Claude Opus 4.666.917/53/1214.2
12Minimax M2.766.938/21/2111.8
13Step 3.5 Flash66.836/34/1211.1
14GPT-5.3 Codex66.234/37/114.8
15Gemini 3.1 Pro Preview63.828/26/2611.8
16Gemini 3.1 Flash Lite Preview61.615/25/3214.8
17GLM-558.732/32/1711.5
18Qwen3.5 122B A10B51.911/35/3411.8
19DeepSeek V3.245.514/51/1810.8
20GPT-5.440.410/35/2717.0
21GPT-5.239.18/34/2118.8
22GPT-5.4 Mini37.07/44/920.3
23Gemini 3 Flash Preview30.65/43/1817.3
24MiMo-V2-Omni22.79/50/319.2
25Trinity Large Preview0.00/79/211.5