Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Spatial-Temporal Reasoning on MMSI
Loading...
41.8
Accuracy
GPT-5
23.808
28.479
33.15
37.821
Feb 28, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-5
2026.02
41.8
Gemini-2.5-Pro
2026.02
36.9
ReMoT-4b-CoT
Model Size=4b, Thinkin...
2026.02
30.8
GPT-4o
2026.02
30.3
InternVL2.5-8B
Model Size=8B
2026.02
28.7
Qwen3-VL-30B-CoT
Model Size=30B, Thinki...
2026.02
28.5
Qwen3-VL-4B-CoT
Model Size=4B, Thinkin...
2026.02
26.8
Qwen2.5-VL-7B
Model Size=7B
2026.02
25.9
LLaVA-Next-7B
Model Size=7B
2026.02
24.5
Feedback
Search any
task
Search any
task