Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Deep Search on MMSrch
Loading...
82.94
Accuracy
Gemini-3 Pro
9.5264
28.5857
47.645
66.7043
Apr 7, 2026
Accuracy
Updated 9d ago
Evaluation Results
Method
Method
Links
Accuracy
Gemini-3 Pro
Evaluation Protocol=Ag...
2026.04
82.94
MTA-DeepSearch-32B
Evaluation Protocol=Ou...
2026.04
82.35
MTA-DeepSearch-8B
Evaluation Protocol=Ou...
2026.04
79.41
GPT-5
Evaluation Protocol=Ag...
2026.04
77.65
Gemini-2.5 Pro
Evaluation Protocol=Ag...
2026.04
77.65
SenseNova-MARS-32B
Evaluation Protocol=Mu...
2026.04
74.27
MM-DeepResearch 32B
Evaluation Protocol=Mu...
2026.04
69
Qwen3-VL-32B-Inst.
Evaluation Protocol=Ag...
2026.04
68.52
SenseNova-MARS-8B
Evaluation Protocol=Mu...
2026.04
67.84
Gemini-3-pro
Evaluation Protocol=Di...
2026.04
65.88
Qwen3-VL-8B-Inst.
Evaluation Protocol=Ag...
2026.04
57.06
Webwatcher-32B
Evaluation Protocol=Mu...
2026.04
55.3
MMSearch-R1-7B
Evaluation Protocol=Mu...
2026.04
53.8
Webwatcher-7B
Evaluation Protocol=Mu...
2026.04
49.1
Gemini-2.5-pro
Evaluation Protocol=Di...
2026.04
41.76
GPT-5
Evaluation Protocol=Di...
2026.04
36.47
Qwen3-VL-32B-Inst.
Evaluation Protocol=Di...
2026.04
17.65
Qwen3-VL-8B-Inst.
Evaluation Protocol=Di...
2026.04
12.35
Feedback
Search any
task
Search any
task