Share your thoughts, 1 month free Claude Pro on usSee more

Spatio-temporal reasoning on STCR

100Accuracy

Human Perception

Updated 5d ago

Evaluation Results

Method	Links
Human Perception 2026.04		100
Human Perception 2026.04		100
Human Perception 2026.04		100
Gemini-2.5-Pro 2026.04		100
Human Perception 2026.04		99.1
Human Perception 2026.04		99.1
Seed1.6 2026.04		98.3
Human Perception 2026.04		98.2
Human Perception 2026.04		97.3
Human Perception 2026.04		97.3
Doubao-1.5-pro 2026.04		96
Doubao-1.5-pro 2026.04		90
Gemini-2.5-Pro 2026.04		89.7
STCR-Tag 2026.04		88.7
STCR-Tag 2026.04		88.6
STCR-Tag 2026.04		88.6
STCR-Tag 2026.04		87.7
STCR-Tag 2026.04		87.1
Seed1.6 2026.04		86.8
STCR-Tag 2026.04		86.2
Doubao-1.5-pro 2026.04		86
STCR-Tag 2026.04		84.8
Seed1.6 2026.04		83.2
Seed1.6 2026.04		82.9
STCR-Tag 2026.04		82.4
DeepSeek-VL2 2026.04		81
Gemini-2.5-Pro 2026.04		80.9
GPT-4o 2026.04		79.2
GPT-4o 2026.04		79.2
GPT-4o 2026.04		79.2
GPT-4o 2026.04		79.2
GPT-o4mini-high 2026.04		78.6
GPT-o4mini-high 2026.04		78.1
GPT-4o 2026.04		77.8
STCR-CoT 2026.04		77.8
DeepSeek-VL2 2026.04		77.4
GPT-o4mini-high 2026.04		77.3
Gemini-2.5-Pro 2026.04		77.2
GPT-4o 2026.04		76.7
STCR-CoT 2026.04		76.7
Doubao-1.5-pro 2026.04		76
STCR-CoT 2026.04		75.6
GPT-o4mini-high 2026.04		75.5
Gemini-2.5-Pro 2026.04		75
Gemini-2.5-Pro 2026.04		75
STCR-CoT 2026.04		74.5
STCR-CoT 2026.04		73.7
Seed1.6 2026.04		73.3
GPT-o4mini 2026.04		72.8
Gemini-2.5-Pro 2026.04		72.8
GPT-o4mini-high 2026.04		72.7
GPT-o4mini-high 2026.04		72.3
STCR-CoT 2026.04		72.2
GPT-o4mini-high 2026.04		71.8
GPT-4o 2026.04		71.7
Gemini-2.5-Pro 2026.04		71.3
GPT-4o 2026.04		71.1
Seed1.6 2026.04		70.6
GPT-o4mini-high 2026.04		70.5
GPT-o4mini 2026.04		70.3
GPT-o4mini 2026.04		70.3
STCR-CoT 2026.04		70.2
GPT-o4mini 2026.04		70
DeepSeek-VL2 2026.04		69.1
STCR-CoT 2026.04		68.3
DeepSeek-VL2 2026.04		67.8
GPT-o4mini 2026.04		67.7
GPT-o4mini 2026.04		67.7
GPT-o4mini 2026.04		67.5
GPT-o3 2026.04		67.2
DeepSeek-VL2 2026.04		67
DeepSeek-VL2 2026.04		66.9
Seed1.6 2026.04		66.8
GPT-o3 2026.04		66.6
Seed1.6 2026.04		66.2
DeepSeek-VL2 2026.04		65.2
DeepSeek-VL2 2026.04		64.4
GPT-o3 2026.04		64
Doubao-1.5-pro 2026.04		64
GPT-o3 2026.04		62
GPT-o3 2026.04		61.6
GPT-o3 2026.04		61.4
GPT-o4mini 2026.04		60
GPT-o3 2026.04		59.6
GPT-o3 2026.04		59.6
Qwen2.5-VL-7B 2026.04		57.3
Doubao-1.5-pro 2026.04		56.9
Qwen2.5-VL-7B 2026.04		56.5
NVILA-8B 2026.04		56.1
Qwen2.5-VL-7B 2026.04		56.1
Doubao-1.5-pro 2026.04		56
Qwen2.5-VL-7B 2026.04		56
Qwen2.5-VL-7B 2026.04		55.4
LLaVA-OneVision-7B 2026.04		55.4
Qwen2.5-VL-7B 2026.04		55.2
NVILA-8B 2026.04		55
Qwen2.5-VL-7B 2026.04		55
LLaVA-OneVision-7B 2026.04		54.8
LLaVA-OneVision-7B 2026.04		53.5
Qwen2.5-VL-7B 2026.04		53.1

Showing 100 of 168 rows