The paper releases CSVQA, a Chinese multimodal STEM benchmark of 1,378 questions with human explanations, and reports that the best tested VLM, o1, reaches only 49.6% accuracy.
Llama 2: Open foundation and fine-tuned chat models, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs
The paper releases CSVQA, a Chinese multimodal STEM benchmark of 1,378 questions with human explanations, and reports that the best tested VLM, o1, reaches only 49.6% accuracy.