Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-agent Cooperation on Group Guessing Game
Loading...
73
Trial 1 Accuracy
Qwen3-4B RL finetuned on HanabiRewards
60.52
63.76
67
70.24
Jan 26, 2026
Trial 1 Accuracy
Trial 2 Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Trial 1 Accuracy
Trial 2 Accuracy
Qwen3-4B RL finetuned on HanabiRewards
Backbone=Qwen3-4B, Var...
2026.01
73
71.5
Qwen3-4B-Instruct-2507
Backbone=Qwen3-4B, Var...
2026.01
61
60.5
Feedback
Search any
task
Search any
task