List your company

Overall Performance on MMG2Skill-Bench Average

69.64Success RateMMG2Skill
22.0634.412546.76559.1175Jun 1, 2026

Evaluation results

MethodLinks
MMG2SkillBackbone=Claude-Opus-4.6, Prompting Variant=MMG2Skill2026.0669.64
MMG2SkillBackbone=GPT-5.5, Prompting Variant=MMG2Skill2026.0667.41
MMG2SkillBackbone=Claude-Sonnet-4.6, Prompting Variant=MMG2Skill2026.0664.92
MMG2SkillBackbone=Kimi-K2.6, Prompting Variant=MMG2Skill2026.0658.81
Raw GuideBackbone=Claude-Opus-4.6, Prompting Variant=Raw Guide2026.0656.86
VanillaBackbone=Claude-Opus-4.6, Prompting Variant=Vanilla2026.0656.85
Raw GuideBackbone=GPT-5.5, Prompting Variant=Raw Guide2026.0654.64
MMG2SkillBackbone=Gemini-3.1-Pro-Preview, Prompting Variant=MMG2Skill2026.0654.17
VanillaBackbone=GPT-5.5, Prompting Variant=Vanilla2026.0654.08
MMG2SkillBackbone=Qwen3.6-Plus, Prompting Variant=MMG2Skill2026.0651.94
Raw GuideBackbone=Claude-Sonnet-4.6, Prompting Variant=Raw Guide2026.0648.89
VanillaBackbone=Claude-Sonnet-4.6, Prompting Variant=Vanilla2026.0648.81
VanillaBackbone=Kimi-K2.6, Prompting Variant=Vanilla2026.0644.36
Raw GuideBackbone=Kimi-K2.6, Prompting Variant=Raw Guide2026.0644.08
VanillaBackbone=Gemini-3.1-Pro-Preview, Prompting Variant=Vanilla2026.0635.82
Raw GuideBackbone=Gemini-3.1-Pro-Preview, Prompting Variant=Raw Guide2026.0631.94
VanillaBackbone=Qwen3.6-Plus, Prompting Variant=Vanilla2026.0626.67
Raw GuideBackbone=Qwen3.6-Plus, Prompting Variant=Raw Guide2026.0623.89