List your company

Sub-Goal Completion on AppWorld 1.0 (test_challenge)

95.4SGCASSAY
9.70431.95254.276.448Jun 13, 2026

Evaluation results

MethodLinks
ASSAYModel=GPT-5.42026.0695.4
ASSAYModel=Sonnet 4.52026.0693.5
ASSAYModel=Gemini 2.52026.0691.8
ReActModel=GPT-5.42026.0691.7
ReActModel=Sonnet 4.52026.0688.7
ReActModel=Gemini 2.52026.0680.5
ASSAYModel=DeepSeek-V32026.0652.5
(Qwen3-14B, wt-tuned)Model=Leaderboard best*2026.0650.4
ASSAYModel=GPT-5.12026.0648.9
CUGAModel=GPT-4.12026.0648.2
ASSAYModel=GPT-4.12026.0648.2
ACEModel=DeepSeek-V32026.0643.9
ReActModel=GPT-4.12026.0632.4
ReActModel=GPT-5.12026.0630.9
ASSAYModel=GPT-4o2026.0630.2
ACEModel=GPT-5.12026.0628.8
ReActModel=DeepSeek-V32026.0625.2
Gupta et al.Model=GPT-4o2026.0623
ReActModel=GPT-4o2026.0613