List your company

Task success rate on DMV-Bench J=10 1.0

77.2Task Success RateDualMem
-3.08817.75638.659.444Jun 25, 2026

Evaluation results

MethodLinks
DualMemBack-end=Qwen2.5-VL-7B, Steps (stp)=238–259, Probe counts (nr)=4,8212026.0677.2
DualMemBack-end=Gemini 2.5 Flash, Steps (stp)=238–259, Probe counts (nr)=12,3442026.0675.2
M2ABack-end=Qwen2.5-VL-7B, Steps (stp)=238–259, Probe counts (nr)=4,8212026.0664.8
CaptionBack-end=Qwen2.5-VL-7B, Steps (stp)=238–259, Probe counts (nr)=4,8212026.0663.7
M2ABack-end=Gemini 2.5 Flash, Steps (stp)=238–259, Probe counts (nr)=12,3442026.0663
CaptionBack-end=Gemini 2.5 Flash, Steps (stp)=238–259, Probe counts (nr)=12,3442026.0653.4
MMABack-end=Gemini 2.5 Flash, Steps (stp)=238–259, Probe counts (nr)=12,3442026.0641.7
MMABack-end=Qwen2.5-VL-7B, Steps (stp)=238–259, Probe counts (nr)=4,8212026.0641
WorldMMBack-end=Gemini 2.5 Flash, Steps (stp)=238–259, Probe counts (nr)=12,3442026.0639.3
WorldMMBack-end=Qwen2.5-VL-7B, Steps (stp)=238–259, Probe counts (nr)=4,8212026.0632.6
NoMemoryBack-end=Qwen2.5-VL-7B, Steps (stp)=238–259, Probe counts (nr)=4,8212026.060
TextOnlyBack-end=Qwen2.5-VL-7B, Steps (stp)=238–259, Probe counts (nr)=4,8212026.060
NoMemoryBack-end=Gemini 2.5 Flash, Steps (stp)=238–259, Probe counts (nr)=12,3442026.060
TextOnlyBack-end=Gemini 2.5 Flash, Steps (stp)=238–259, Probe counts (nr)=12,3442026.060