MTGBench - Native Reasoning - Russian - Situation Puzzles - Normalized Score: leaderboard
MTGBench Native Reasoning protocol in Russian, Situation Puzzles: speed/survival-normalized score 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: Normalized Score among completed episodes (%). Source: github.com. Saturation forecast: Rough model projection: around 2026. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | gemini-3.1-pro-preview (MTGBench Run: mode=reasoning;effort=unreported;release=ffe4adc59146) | 64.74 | |
| 2 | qwen3-235b-a22b-thinking-2507 (MTGBench Run: mode=reasoning;effort=unreported;release=ffe4adc59146) | 48 | |
| 3 | deepseek-v4-pro (MTGBench Run: mode=reasoning;effort=unreported;release=ffe4adc59146) | 46.79 | |
| 4 | gpt-5.4 (MTGBench Run: mode=reasoning;effort=unreported;release=ffe4adc59146) | 43.79 | |
| 5 | gemini-3-flash-preview (MTGBench Run: mode=reasoning;effort=unreported;release=ffe4adc59146) | 42.47 | |
| 6 | gpt-5.4-mini (MTGBench Run: mode=reasoning;effort=unreported;release=ffe4adc59146) | 42.11 | |
| 7 | gpt-5.4-nano (MTGBench Run: mode=reasoning;effort=unreported;release=ffe4adc59146) | 41.05 | |
| 8 | gemini-3.1-flash-lite (MTGBench Run: mode=reasoning;effort=unreported;release=ffe4adc59146) | 40.68 | |
| 9 | qwen3-30b-a3b-thinking-2507 (MTGBench Run: mode=reasoning;effort=unreported;release=ffe4adc59146) | 39.37 | |
| 10 | gpt-oss-120b (MTGBench Run: mode=reasoning;effort=unreported;release=ffe4adc59146) | 39.16 |
Interactive version: theaggregate.ai/benchmark?slug=mtgbench-native-reasoning-russian-situation-puzzles-normalized-score · How It Works · Data refreshed daily, snapshot 2026-11-05.