Long-context Question Answering on DocMath
29.02F1 ScoreGLM-4.1V-9B-Thinking VERA
Evaluation results
| Method | Links | |
|---|---|---|
| GLM-4.1V-9B-Thinking VERARAG Strategy=Attention-Guided RAG2026.02 | 29.02 | |
| GLM-4.1V-9B-Thinking Random RAGRAG Strategy=Random RAG2026.02 | 21.99 | |
| GLM-4.1V-9B-Thinking ColPali RAGRAG Strategy=ColPali RAG2026.02 | 21.18 | |
| GLM-4.1V-9B-Thinking Embedding RAGRAG Strategy=Embedding RAG2026.02 | 17.49 | |
| GLM-4.1V-9B-ThinkingRAG Strategy=Direct (None)2026.02 | 15.71 | |
| GlyphRAG Strategy=Direct (None)2026.02 | 13.61 | |
| Qwen3-VL-8B-Instruct VERARAG Strategy=Attention-Guided RAG2026.02 | 9.45 | |
| Qwen3-VL-8B-Instruct Random RAGRAG Strategy=Random RAG2026.02 | 5.61 | |
| Qwen3-VL-8B-Instruct OCR RAGRAG Strategy=OCR RAG2026.02 | 4.72 | |
| Qwen3-VL-8B-InstructRAG Strategy=Direct (None)2026.02 | 3.47 |