List your company

Spatial-Temporal Reasoning on MMSI

41.8AccuracyGPT-5
23.80828.47933.1537.821Feb 28, 2026

Evaluation results

MethodLinks
GPT-52026.0241.8
Gemini-2.5-Pro2026.0236.9
ReMoT-4b-CoTModel Size=4b, Thinking Mode=CoT2026.0230.8
GPT-4o2026.0230.3
InternVL2.5-8BModel Size=8B2026.0228.7
Qwen3-VL-30B-CoTModel Size=30B, Thinking Mode=CoT2026.0228.5
Qwen3-VL-4B-CoTModel Size=4B, Thinking Mode=CoT2026.0226.8
Qwen2.5-VL-7BModel Size=7B2026.0225.9
LLaVA-Next-7BModel Size=7B2026.0224.5