MTGBench - Answer Only - Russian - Wheel of Fortune - Win Rate: leaderboard

MTGBench Answer Only protocol in Russian, Wheel of Fortune: win rate among completed episodes. Seven multi-turn puzzle games measure deduction, planning, information gathering and consistency. Incomplete/missing episodes follow the native exclusion policy; completed sample sizes and exact prompt/native-reasoning modes are retained. Overall equally averages seven game means.

Metric: Win Rate among completed episodes (%). Source: github.com. Saturation forecast: Rough model projection: around 2026. 12 models tracked.

Top models

#ModelScoreOverall rank
1deepseek-v4-pro (MTGBench Run: mode=answer_only;effort=unreported;release=ffe4adc59146)99
2gemini-3-flash-preview (MTGBench Run: mode=answer_only;effort=unreported;release=ffe4adc59146)99
3gpt-5.4 (MTGBench Run: mode=answer_only;effort=unreported;release=ffe4adc59146)98
4deepseek-v3.1-terminus (MTGBench Run: mode=answer_only;effort=unreported;release=ffe4adc59146)96
5gpt-4.1 (MTGBench Run: mode=answer_only;effort=unreported;release=ffe4adc59146)96
6deepseek-v4-flash (MTGBench Run: mode=answer_only;effort=unreported;release=ffe4adc59146)93
7gemini-3.1-flash-lite (MTGBench Run: mode=answer_only;effort=unreported;release=ffe4adc59146)88
8qwen3-235b-a22b-instruct-2507 (MTGBench Run: mode=answer_only;effort=unreported;release=ffe4adc59146)86
9qwen3.5-35b-a3b (MTGBench Run: mode=answer_only;effort=unreported;release=ffe4adc59146)75
10qwen3-30b-a3b-instruct-2507 (MTGBench Run: mode=answer_only;effort=unreported;release=ffe4adc59146)65

Interactive version: theaggregate.ai/benchmark?slug=mtgbench-answer-only-russian-wheel-of-fortune-win-rate · How It Works · Data refreshed daily, snapshot 2026-11-05.