List your company

Proactive Assistance on Pro2Bench EK

0.9G-Mean F1Qwen3.6-VL-27B
-0.0360.2070.450.693Jun 3, 2026

Evaluation results

MethodLinks
Qwen3.6-VL-27BFT=true, PWR=true, Architecture=split duplex+planner2026.060.90.36
Llama 4-MaverickFT=true, PWR=true, Architecture=split duplex+planner2026.060.80.67
Llama 4-MaverickFT=true, Architecture=monolithic2026.060.710.51
Claude Opus 4.6Architecture=monolithic, Mode=zero-shot2026.060.520.29
Gemini 3.1 ProArchitecture=monolithic, Mode=zero-shot2026.060.50.34
Llama 4-MaverickArchitecture=monolithic2026.060.50.36
Qwen3.6-VL-27BFT=true, Architecture=monolithic2026.060.470.3
Qwen3-VL-235BArchitecture=monolithic2026.060.460.32
Qwen3.6-VL-27BArchitecture=monolithic2026.060.170.45
GPT-5.2Architecture=monolithic, Mode=zero-shot2026.060—