TACO: Tool-Augmented Credit Optimization for Agentic Tool Use
Open paper
Benchmark
Model
Rank
Results
chart-question-answering-on-chartqa
TACO (Qwen2.5-VL-7B, 7B)
–
1:1 Accuracy: 86.7
vision-language-understanding-on-mmstar
TACO (Qwen3-VL-8B, 8B)
–
Accuracy: 72.1
Rank counts only results with a code link.