List your company

Agentic Reasoning on ALFWorld

76.02Success RateEAPO-8B
30.05241.98653.9265.854May 8, 2026May 9, 2026

Evaluation results

MethodLinks
EAPO-8BModel Category=Ours2026.0576.02
EAPO-8B2026.0576.02
EAPO-4BModel Category=Ours2026.0569
EAPO-4B2026.0569
HTPOBase Model=Qwen3-8B2026.0561.4
LAMERCategory=Training Method2026.0561.26
DAPOBase Model=Qwen3-8B2026.0560
GRPOBase Model=Qwen3-8B2026.0559.3
EAPO-1.7B/2BModel Category=Ours2026.0558.5
EAPO-1.7B/2B2026.0558.5
GiGPOCategory=Training Method2026.0556.76
Claude-4-Sonnet-0929Model Category=Closed-source Models2026.0556.09
Claude-4-Sonnet-0929Category=Closed-source2026.0556.09
DeepMiner-Mano-72BModel Category=Closed-source Models2026.0554.12
DeepMiner-Mano-72BCategory=Closed-source2026.0554.12
DAPOCategory=Training Method2026.0551.86
UI-TARS-2-2509Model Category=Closed-source Models2026.0551.21
UI-TARS-2-2509Category=Closed-source2026.0551.21
Qwen3-VL-235B-A22BModel Category=Open-source Models2026.0550.81
Qwen3-VL-235B-A22BCategory=Open-source2026.0550.81
Qwen3-VL-32BModel Category=Open-source Models2026.0549.69
Claude-3.7-SonnetModel Category=Closed-source Models2026.0548.61
Seed1.5-VL-250717Model Category=Closed-source Models2026.0547.53
Seed1.5-VL-250717Category=Closed-source2026.0547.53
DeepMiner-Mano-7BModel Category=Closed-source Models2026.0546.27
GRPOCategory=Training Method2026.0546.13
DART-GUI-7BModel Category=Open-source Models2026.0545.78
DART-GUI-7BCategory=Open-source2026.0545.78
OpenAI CUAModel Category=Closed-source Models2026.0544.88
UI-TARS-72B-dpoModel Category=Open-source Models2026.0544.36
OpenAI CUA o3Model Category=Closed-source Models2026.0542.31
OpenAI CUA o3Category=Closed-source2026.0542.31
OpenCUA-32BModel Category=Open-source Models2026.0539.99
OpenCUA-32BCategory=Open-source2026.0539.99
GUI-Owl-7BModel Category=Open-source Models2026.0538.47
GUI-Owl-7BCategory=Open-source2026.0538.47
ARPOModel Category=Open-source Models2026.0537.2
ARPOCategory=Open-source2026.0537.2
TianXi-Action-7BModel Category=Closed-source Models2026.0536.57
TianXi-Action-7BCategory=Closed-source2026.0536.57
ZeroGUIModel Category=Open-source Models2026.0535.76
ZeroGUICategory=Open-source2026.0535.76
OpenCUA-7BModel Category=Open-source Models2026.0534.69
UI-TARS-7BModel Category=Open-source Models2026.0531.82
UI-TARS-7BCategory=Open-source2026.0531.82