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

Agentic Reasoning on ALFWorld

76.02Success Rate

EAPO-8B

Updated 22d ago

Evaluation Results

Method	Links
EAPO-8B 2026.05		76.02
EAPO-8B 2026.05		76.02
EAPO-4B 2026.05		69
EAPO-4B 2026.05		69
HTPO 2026.05		61.4
LAMER 2026.05		61.26
DAPO 2026.05		60
GRPO 2026.05		59.3
EAPO-1.7B/2B 2026.05		58.5
EAPO-1.7B/2B 2026.05		58.5
GiGPO 2026.05		56.76
Claude-4-Sonnet-0929 2026.05		56.09
Claude-4-Sonnet-0929 2026.05		56.09
DeepMiner-Mano-72B 2026.05		54.12
DeepMiner-Mano-72B 2026.05		54.12
DAPO 2026.05		51.86
UI-TARS-2-2509 2026.05		51.21
UI-TARS-2-2509 2026.05		51.21
Qwen3-VL-235B-A22B 2026.05		50.81
Qwen3-VL-235B-A22B 2026.05		50.81
Qwen3-VL-32B 2026.05		49.69
Claude-3.7-Sonnet 2026.05		48.61
Seed1.5-VL-250717 2026.05		47.53
Seed1.5-VL-250717 2026.05		47.53
DeepMiner-Mano-7B 2026.05		46.27
GRPO 2026.05		46.13
DART-GUI-7B 2026.05		45.78
DART-GUI-7B 2026.05		45.78
OpenAI CUA 2026.05		44.88
UI-TARS-72B-dpo 2026.05		44.36
OpenAI CUA o3 2026.05		42.31
OpenAI CUA o3 2026.05		42.31
OpenCUA-32B 2026.05		39.99
OpenCUA-32B 2026.05		39.99
GUI-Owl-7B 2026.05		38.47
GUI-Owl-7B 2026.05		38.47
ARPO 2026.05		37.2
ARPO 2026.05		37.2
TianXi-Action-7B 2026.05		36.57
TianXi-Action-7B 2026.05		36.57
ZeroGUI 2026.05		35.76
ZeroGUI 2026.05		35.76
OpenCUA-7B 2026.05		34.69
UI-TARS-7B 2026.05		31.82
UI-TARS-7B 2026.05		31.82