Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Deep Search on BC-VL
Loading...
53.77
Accuracy
MTA-DeepSearch-32B
18.7012
27.8056
36.91
46.0144
Apr 7, 2026
Accuracy
Updated 9d ago
Evaluation Results
Method
Method
Links
Accuracy
MTA-DeepSearch-32B
Evaluation Protocol=Ou...
2026.04
53.77
Gemini-3 Pro
Evaluation Protocol=Ag...
2026.04
51.78
GPT-5
Evaluation Protocol=Ag...
2026.04
51.63
Gemini-2.5 Pro
Evaluation Protocol=Ag...
2026.04
49.5
MTA-DeepSearch-8B
Evaluation Protocol=Ou...
2026.04
44.36
MM-DeepResearch 32B
Evaluation Protocol=Mu...
2026.04
43
GPT-5
Evaluation Protocol=Di...
2026.04
41.6
Gemini-3-pro
Evaluation Protocol=Di...
2026.04
41.35
Gemini-2.5-pro
Evaluation Protocol=Di...
2026.04
39.85
Qwen3-VL-32B-Inst.
Evaluation Protocol=Ag...
2026.04
38.69
Qwen3-VL-8B-Inst.
Evaluation Protocol=Ag...
2026.04
35.89
Webwatcher-32B
Evaluation Protocol=Mu...
2026.04
26.7
Qwen3-VL-32B-Inst.
Evaluation Protocol=Di...
2026.04
24.81
Webwatcher-7B
Evaluation Protocol=Mu...
2026.04
20.3
Qwen3-VL-8B-Inst.
Evaluation Protocol=Di...
2026.04
20.05
Feedback
Search any
task
Search any
task