Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Game Interaction on MMG2Skill-Bench Game
Loading...
83.33
Success Rate
MMG2Skill
7.0668
26.8659
46.665
66.4641
Jun 1, 2026
Success Rate
Updated 1d ago
Evaluation Results
Method
Method
Links
Success Rate
MMG2Skill
Backbone=Claude-Opus-4...
2026.06
83.33
MMG2Skill
Backbone=GPT-5.5, Prom...
2026.06
80
Raw Guide
Backbone=GPT-5.5, Prom...
2026.06
76.67
Vanilla
Backbone=GPT-5.5, Prom...
2026.06
73.33
MMG2Skill
Backbone=Claude-Sonnet...
2026.06
73.33
Vanilla
Backbone=Claude-Opus-4...
2026.06
66.67
Raw Guide
Backbone=Claude-Opus-4...
2026.06
66.67
MMG2Skill
Backbone=Gemini-3.1-Pr...
2026.06
66.67
Raw Guide
Backbone=Claude-Sonnet...
2026.06
60
Vanilla
Backbone=Claude-Sonnet...
2026.06
56.67
MMG2Skill
Backbone=Kimi-K2.6, Pr...
2026.06
46.67
MMG2Skill
Backbone=Qwen3.6-Plus,...
2026.06
46.67
Vanilla
Backbone=Gemini-3.1-Pr...
2026.06
33.33
Raw Guide
Backbone=Gemini-3.1-Pr...
2026.06
23.33
Vanilla
Backbone=Kimi-K2.6, Pr...
2026.06
16.67
Raw Guide
Backbone=Kimi-K2.6, Pr...
2026.06
16.67
Vanilla
Backbone=Qwen3.6-Plus,...
2026.06
16.67
Raw Guide
Backbone=Qwen3.6-Plus,...
2026.06
10
Feedback
Search any
task
Search any
task