Strategic Decision Making on MMG2Skill-Bench Strategy
69.17Success RateMMG2Skill
Evaluation Results
| Method | Links | |
|---|---|---|
| MMG2SkillBackbone=Qwen3.6-Plus, Prompting Variant=MMG2Skill2026.06 | 69.17 | |
| MMG2SkillBackbone=GPT-5.5, Prompting Variant=MMG2Skill2026.06 | 65 | |
| MMG2SkillBackbone=Claude-Sonnet-4.6, Prompting Variant=MMG2Skill2026.06 | 61.67 | |
| MMG2SkillBackbone=Claude-Opus-4.6, Prompting Variant=MMG2Skill2026.06 | 60.83 | |
| MMG2SkillBackbone=Gemini-3.1-Pro-Preview, Prompting Variant=MMG2Skill2026.06 | 60.83 | |
| VanillaBackbone=Gemini-3.1-Pro-Preview, Prompting Variant=Vanilla2026.06 | 54.17 | |
| MMG2SkillBackbone=Kimi-K2.6, Prompting Variant=MMG2Skill2026.06 | 52.5 | |
| Raw GuideBackbone=Gemini-3.1-Pro-Preview, Prompting Variant=Raw Guide2026.06 | 52.5 | |
| Raw GuideBackbone=GPT-5.5, Prompting Variant=Raw Guide2026.06 | 50 | |
| VanillaBackbone=GPT-5.5, Prompting Variant=Vanilla2026.06 | 49.17 | |
| VanillaBackbone=Qwen3.6-Plus, Prompting Variant=Vanilla2026.06 | 48.33 | |
| VanillaBackbone=Kimi-K2.6, Prompting Variant=Vanilla2026.06 | 46.67 | |
| Raw GuideBackbone=Claude-Opus-4.6, Prompting Variant=Raw Guide2026.06 | 44.17 | |
| Raw GuideBackbone=Qwen3.6-Plus, Prompting Variant=Raw Guide2026.06 | 44.17 | |
| VanillaBackbone=Claude-Opus-4.6, Prompting Variant=Vanilla2026.06 | 41.67 | |
| Raw GuideBackbone=Kimi-K2.6, Prompting Variant=Raw Guide2026.06 | 40.83 | |
| VanillaBackbone=Claude-Sonnet-4.6, Prompting Variant=Vanilla2026.06 | 40 | |
| Raw GuideBackbone=Claude-Sonnet-4.6, Prompting Variant=Raw Guide2026.06 | 39.17 |