Share your thoughts, 1 month free Claude Pro on usSee more

General Competence on G2U Overall

2.8Average Rank (Overall)

Human

Updated 19d ago

Evaluation Results

Method	Links
Human 2025.11		2.8
Qwen3-VL-8B 2025.11		4.9
DQN 2025.11		10.6
DreamerV3 2025.11		10.7
DQN 2025.11		11.4
PPO 2025.11		12
DQN 2025.11		12.2
GenieRedux 2025.11		12.4
DreamerV3 2025.11		13.1
Qwen3-VL-8B-BC 2025.11		13.3
GPT-5 2025.11		13.3
GenieRedux 2025.11		14.2
PPO 2025.11		14.7
PPO 2025.11		14.8
DreamerV3 2025.11		15.4
GenieRedux 2025.11		16.1
GPT-4o 2025.11		16.4
ACT-BC 2025.11		16.6
GPT-5 2025.11		16.8
Qwen3-VL-30B-A3B 2025.11		17.6
GPT-5 2025.11		17.9
Qwen3-VL-8B 2025.11		18.2
V-JEPA2 2025.11		18.3
GPT-4o 2025.11		18.8
GPT-4o 2025.11		19.4
V-JEPA2 2025.11		20.2
V-JEPA2 2025.11		20.8
Qwen3-VL-30B-A3B 2025.11		22.4
Qwen3-VL-30B-A3B 2025.11		22.7
Random 2025.11		26.9