Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Deep Search on FVQA (Accuracy)
Loading...
76.67
Accuracy
Gemini-3 Pro
22.7356
36.7378
50.74
64.7422
Apr 7, 2026
Accuracy
Updated 9d ago
Evaluation Results
Method
Method
Links
Accuracy
Gemini-3 Pro
Evaluation Protocol=Ag...
2026.04
76.67
MTA-DeepSearch-32B
Evaluation Protocol=Ou...
2026.04
76
MTA-DeepSearch-8B
Evaluation Protocol=Ou...
2026.04
73.06
SenseNova-MARS-32B
Evaluation Protocol=Mu...
2026.04
72.61
Gemini-2.5 Pro
Evaluation Protocol=Ag...
2026.04
72.33
GPT-5
Evaluation Protocol=Ag...
2026.04
72.28
MM-DeepResearch 32B
Evaluation Protocol=Mu...
2026.04
70.1
SenseNova-MARS-8B
Evaluation Protocol=Mu...
2026.04
67.11
Qwen3-VL-32B-Inst.
Evaluation Protocol=Ag...
2026.04
66.94
Qwen3-VL-8B-Inst.
Evaluation Protocol=Ag...
2026.04
64.22
Gemini-3-pro
Evaluation Protocol=Di...
2026.04
58.94
MMSearch-R1-7B
Evaluation Protocol=Mu...
2026.04
58.4
Gemini-2.5-pro
Evaluation Protocol=Di...
2026.04
54.5
GPT-5
Evaluation Protocol=Di...
2026.04
50.83
Qwen3-VL-8B-Inst.
Evaluation Protocol=Di...
2026.04
26.94
Qwen3-VL-32B-Inst.
Evaluation Protocol=Di...
2026.04
24.81
Feedback
Search any
task
Search any
task