List your company

Visual Navigation on Frozen-Lake 4x4 Grid

55AccuracyQwen3-VL + V-ABS
8.220.3532.544.65May 11, 2026

Evaluation results

MethodLinks
Qwen3-VL + V-ABSBackbone=Qwen3-VL-8B, Strategy=V-ABS2026.0555
GPT-4o + V-ABSBackbone=GPT-4o, Strategy=V-ABS2026.0550
Qwen2.5-VL + V-ABSBackbone=Qwen2.5-VL-7B, Strategy=V-ABS2026.0545
GPT-4o + VisuoThinkBackbone=GPT-4o, Strategy=VisuoThink2026.0535
Intern-VL3-8B + V-ABSBackbone=Intern-VL3-8B, Strategy=V-ABS2026.0530
Qwen3-VL-8BBackbone=Qwen3-VL-8B2026.0525
GPT-4oBackbone=GPT-4o2026.0520
Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B2026.0515
Intern-VL3-8BBackbone=Intern-VL3-8B2026.0510