List your company

Behavior Tree Synthesis on 10 Real-world User Requests 1.0 (test)

100TSR (%)Gemini 3 Flash
-4235077Apr 3, 2026

Evaluation results

MethodLinks
Gemini 3 FlashProtocol=one-shot2026.0410010006.233.60.5652.2100—
Pixtral-12BAblation ID=A12026.041001000623.10.5930.110061.85
Pixtral-12BAblation ID=A92026.04901000622.10.5435.810060.12
GPT-5Protocol=one-shot2026.04808006.240.40.586480—
Pixtral-12BAblation ID=A102026.048010010625.10.5838.49052.24
Pixtral-12BAblation ID=A52026.047010030621.80.4832.19054.42
Pixtral-12BAblation ID=A172026.04701000621.40.5134.110059.88
Pixtral-12BAblation ID=A112026.046090205.419.20.4228.110054.39
Pixtral-12BAblation ID=A162026.045090104.815.60.3824.58058.21
Pixtral-12BAblation ID=A22026.044010060612.80.333.410058.45
Pixtral-12BAblation ID=A82026.044010060612.80.333.410061.64
Pixtral-12BAblation ID=A72026.04304002.16.70.210.13040.54
Pixtral-12BAblation ID=A122026.043070304.214.50.3119.88054.45
Pixtral-12BAblation ID=A42026.04205003.411.20.2815.610054.66
Pixtral-12BAblation ID=A142026.042040102.47.10.1812.44058.27
Pixtral-12BAblation ID=A32026.04101000.61.90.0631053.86
Pixtral-12BAblation ID=A152026.041040201.85.20.128.42055.45
GPT-5Protocol=zero-shot2026.0400000000—
Gemini 3 FlashProtocol=zero-shot2026.0400000000—
Pixtral-12BProtocol=zero-shot2026.040000000052.8
Pixtral-12BAblation ID=A62026.0401000.82.10.043.5018.42
Pixtral-12BAblation ID=A132026.0400000000309.71