List your company

Agentic task solving on AppWorld

90TGCA-Evolve
-3.620.74569.3Dec 12, 2025Dec 20, 2025Dec 28, 2025Jan 5, 2026Jan 13, 2026Jan 21, 2026Jan 30, 2026

Evaluation results

MethodLinks
A-EvolveBackbone=Claude Sonnet 4.52026.019096.47
AWMBackbone=Claude Sonnet 4.52026.018897.32
A-EvolveBackbone=GPT 52026.018897.02
VanillaBackbone=Claude Sonnet 4.52026.018694.94
AWMBackbone=GPT 52026.018494.08
APEBackbone=GPT 52026.018295
A-EvolveBackbone=Gemini 3 Flash2026.018292.05
APEBackbone=Claude Sonnet 4.52026.018085
VanillaBackbone=GPT 52026.018094.15
Vanilla modelBase Model=DeepSeek-V3.2-Exp, Mem=N/A, Len=N/A2025.1273.2—
MNLBase Model=DeepSeek-V3.2-Exp, Mem=0, Len=02025.1273.2—
MementoBase Model=DeepSeek-V3.2-Exp, Mem=56, Len=6022025.1264.2—
A-EvolveBackbone=Claude Haiku 4.52026.016484.31
A-EvolveBackbone=Claude Sonnet 42026.015688.21
VanillaBackbone=Gemini 3 Flash2026.015680.45
APEBackbone=Gemini 3 Flash2026.015284
AWMBackbone=Gemini 3 Flash2026.015287.75
AWMBackbone=Claude Sonnet 42026.015086.29
AWMBackbone=Claude Haiku 4.52026.014665.76
ACEBase Model=DeepSeek-V3.2-Exp, Mem=8, Len=69022025.1244.6—
APEBackbone=Claude Sonnet 42026.014482
VanillaBackbone=Claude Sonnet 42026.014279.42
VanillaBackbone=Claude Haiku 4.52026.013251.16
APEBackbone=Claude Haiku 4.52026.013056
MNLBase Model=Qwen3-8B, Mem=12, Len=3912025.1214.3—
Vanilla modelBase Model=Qwen3-8B, Mem=N/A, Len=N/A2025.1212.5—
MementoBase Model=Qwen3-8B, Mem=50, Len=7072025.1212.5—
ACEBase Model=Qwen3-8B, Mem=61, Len=32172025.120—