List your company

Sub-Goal Completion on AppWorld 1.0 (test_normal)

97.2Sub-Goal Completion RateASSAY
29.49647.07364.6582.227Jun 13, 2026

Evaluation results

MethodLinks
ASSAYModel=Sonnet 4.52026.0697.2
ASSAYModel=GPT-5.42026.0696.7
ASSAYModel=Gemini 2.52026.0695.5
ReActModel=Sonnet 4.52026.0694
ReActModel=GPT-5.42026.0691.9
ReActModel=Gemini 2.52026.0687.8
(Qwen3-14B, wt-tuned)Model=Leaderboard best*2026.0680.4
ASSAYModel=GPT-5.12026.0671.4
ASSAYModel=DeepSeek-V32026.0671.4
ACEModel=DeepSeek-V32026.0666.1
CUGAModel=GPT-4.12026.0662.5
ASSAYModel=GPT-4.12026.0660.7
ASSAYModel=GPT-4o2026.0658.9
Gupta et al.Model=GPT-4o2026.0657.1
ACEModel=GPT-5.12026.0655.4
ReActModel=DeepSeek-V32026.0648.2
ReActModel=GPT-5.12026.0646.4
ReActModel=GPT-4.12026.0646.4
ReActModel=GPT-4o2026.0632.1