List your company

Spatial-Temporal Reasoning on VSI

58.8AccuracyReMoT-4b-CoT
31.96838.93445.952.866Feb 28, 2026

Evaluation results

MethodLinks
ReMoT-4b-CoTModel Size=4b, Thinking Mode=CoT2026.0258.8
Qwen3-VL-30B-CoTModel Size=30B, Thinking Mode=CoT2026.0256.1
Qwen3-VL-4B-CoTModel Size=4B, Thinking Mode=CoT2026.0255.2
GPT-52026.0255
Gemini-2.5-Pro2026.0253.6
InternVL2.5-8BModel Size=8B2026.0246.6
GPT-4o2026.0242.5
LLaVA-Next-7BModel Size=7B2026.0235.6
Qwen2.5-VL-7BModel Size=7B2026.0233