List your company

Proactive Assistance on Pro2Bench EE4D

89G-Mean F1Qwen3.6-VL-27B
7.8828.945071.06Jun 3, 2026

Evaluation results

MethodLinks
Qwen3.6-VL-27BFT=true, PWR=true, Architecture=split duplex+planner2026.068952
Llama 4-MaverickFT=true, PWR=true, Architecture=split duplex+planner2026.067358
Llama 4-MaverickFT=true, Architecture=monolithic2026.067241
Qwen3.6-VL-27BFT=true, Architecture=monolithic2026.066143
Llama 4-MaverickArchitecture=monolithic2026.065036
Claude Opus 4.6Architecture=monolithic, Mode=zero-shot2026.064832
Gemini 3.1 ProArchitecture=monolithic, Mode=zero-shot2026.063827
Qwen3.6-VL-27BArchitecture=monolithic2026.063628
GPT-5.2Architecture=monolithic, Mode=zero-shot2026.0634—
Qwen3-VL-235BArchitecture=monolithic2026.061113