List your company
ResearchFormerly WizWand

Chart Question Answering on ChartQA (Accuracy, Rel. (%))

83AccuracyFull Model
11.34429.94748.5567.153Oct 30, 2025Dec 8, 2025Jan 17, 2026Feb 26, 2026Apr 6, 2026May 16, 2026Jun 25, 2026
Updated 4mo ago

Evaluation results

MethodLinks
Full ModelBackbone=Qwen2-VL-7B, Sparsity Ratio=0%2026.0483100
MaLoRAModel=Qwen2.5-VL-7B, Training examples=28.3k2025.1080.84—
LoRAModel=Qwen2.5-VL-7B, Training examples=28.3k2025.1080.72—
TopoVLMBackbone=Qwen2-VL-7B, Sparsity Ratio=50%2026.0480.495.4
MaLoRAModel=Qwen3-VL-8B, Training examples=28.3k2025.1080.24—
LoRAModel=Qwen3-VL-8B, Training examples=28.3k2025.1079.88—
BaseModel=Qwen3-VL-8B, Training examples=28.3k2025.1079.04—
TAMPBackbone=Qwen2-VL-7B, Sparsity Ratio=50%2026.0478.993.2
QLoRAModel=Qwen3-VL-8B, Training examples=28.3k2025.1077.88—
InternViT-2.5-6BBase LLM=Qwen2.5 - 7B, Size=6.0B, AnyRes=false, Discrete=false2026.0677.4—
LLM-StreamlineBackbone=Qwen2-VL-7B, Sparsity Ratio=50%2026.0476.591.2
ECoFLaPBackbone=Qwen2-VL-7B, Sparsity Ratio=50%2026.0475.290.5
SparseGPTBackbone=Qwen2-VL-7B, Sparsity Ratio=50%2026.0474.390.1
WandaBackbone=Qwen2-VL-7B, Sparsity Ratio=50%2026.0473.689.3
OWLBackbone=Qwen2-VL-7B, Sparsity Ratio=50%2026.0472.888.4
SigLIP2-gBase LLM=Qwen2.5 - 7B, Size=1.1B, AnyRes=false, Discrete=false2026.0672.8—
ViQBase LLM=Qwen2.5 - 7B, Size=1.3B, AnyRes=true, Discrete=true2026.0672.8—
AIMv2-HBase LLM=Qwen2.5 - 7B, Size=0.7B, AnyRes=false, Discrete=false2026.0672.5—
LLM-PrunerBackbone=Qwen2-VL-7B, Sparsity Ratio=50%2026.0472.488.6
OryxViTBase LLM=Qwen2.5 - 7B, Size=0.4B, AnyRes=true, Discrete=false2026.0672.1—
BaseModel=Qwen2.5-VL-7B, Training examples=28.3k2025.1071.84—
QLoRAModel=Qwen2.5-VL-7B, Training examples=28.3k2025.1071.76—
InternViT-2.5Base LLM=Qwen2.5 - 1.5B, Size=0.3B, AnyRes=false, Discrete=false2026.0669.2—
InternViT-2.5-6BBase LLM=Qwen2.5 - 1.5B, Size=6.0B, AnyRes=false, Discrete=false2026.0667.8—
ViQBase LLM=Qwen2.5 - 1.5B, Size=1.3B, AnyRes=true, Discrete=true2026.0665.2—
OAI-CLIP-LBase LLM=Qwen2.5 - 7B, Size=0.3B, AnyRes=false, Discrete=false2026.0665.1—
AIMv2-HBase LLM=Qwen2.5 - 1.5B, Size=0.7B, AnyRes=false, Discrete=false2026.0662.5—
OryxViTBase LLM=Qwen2.5 - 1.5B, Size=0.4B, AnyRes=true, Discrete=false2026.0662.1—
SigLIP2-gBase LLM=Qwen2.5 - 1.5B, Size=1.1B, AnyRes=false, Discrete=false2026.0662—
DinoV2-gBase LLM=Qwen2.5 - 1.5B, Size=1.1B, AnyRes=false, Discrete=false2026.0661.8—
OAI-CLIP-LBase LLM=Qwen2.5 - 1.5B, Size=0.3B, AnyRes=false, Discrete=false2026.0655—
UniTokBase LLM=Qwen2.5 - 1.5B, Size=0.3B, AnyRes=false, Discrete=true2026.0643.8—
MaLoRAModel=LLaVA-1.5-7B, Training examples=28.3k2025.1020.28—
LoRAModel=LLaVA-1.5-7B, Training examples=28.3k2025.1019—
QLoRAModel=LLaVA-1.5-7B, Training examples=28.3k2025.1018.12—
BaseModel=LLaVA-1.5-7B, Training examples=28.3k2025.1014.36—
QLIPBase LLM=Qwen2.5 - 1.5B, Size=0.3B, AnyRes=false, Discrete=true2026.0614.1—