Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Deep Search on HR-MMSrch
Loading...
54.43
Accuracy
SenseNova-MARS-32B
2.5964
16.0532
29.51
42.9668
Apr 7, 2026
Accuracy
Updated 9d ago
Evaluation Results
Method
Method
Links
Accuracy
SenseNova-MARS-32B
Evaluation Protocol=Mu...
2026.04
54.43
MTA-DeepSearch-32B
Evaluation Protocol=Ou...
2026.04
53.95
Gemini-3 Pro
Evaluation Protocol=Ag...
2026.04
53.2
GPT-5
Evaluation Protocol=Ag...
2026.04
52.13
Gemini-2.5 Pro
Evaluation Protocol=Ag...
2026.04
48.2
MTA-DeepSearch-8B
Evaluation Protocol=Ou...
2026.04
47.54
SenseNova-MARS-8B
Evaluation Protocol=Mu...
2026.04
41.64
Qwen3-VL-32B-Inst.
Evaluation Protocol=Ag...
2026.04
38.69
Qwen3-VL-8B-Inst.
Evaluation Protocol=Ag...
2026.04
32.13
Gemini-3-pro
Evaluation Protocol=Di...
2026.04
23.61
MMSearch-R1-7B
Evaluation Protocol=Mu...
2026.04
20.33
GPT-5
Evaluation Protocol=Di...
2026.04
16.39
Gemini-2.5-pro
Evaluation Protocol=Di...
2026.04
15.41
Qwen3-VL-8B-Inst.
Evaluation Protocol=Di...
2026.04
4.59
Qwen3-VL-32B-Inst.
Evaluation Protocol=Di...
2026.04
4.59
Feedback
Search any
task
Search any
task