Long-context Question Answering on LongBench Pro
34.2F1 ScoreGLM-4.1V-9B-Thinking VERA
Evaluation results
| Method | Links | |
|---|---|---|
| GLM-4.1V-9B-Thinking VERARAG Strategy=Attention-Guided RAG2026.02 | 34.2 | |
| GLM-4.1V-9B-ThinkingRAG Strategy=Direct (None)2026.02 | 31.06 | |
| GlyphRAG Strategy=Direct (None)2026.02 | 28.94 | |
| GLM-4.1V-9B-Thinking Random RAGRAG Strategy=Random RAG2026.02 | 28.84 | |
| Qwen3-VL-8B-Instruct VERARAG Strategy=Attention-Guided RAG2026.02 | 28.74 | |
| GLM-4.1V-9B-Thinking ColPali RAGRAG Strategy=ColPali RAG2026.02 | 28.58 | |
| Qwen3-VL-8B-Instruct Random RAGRAG Strategy=Random RAG2026.02 | 28 | |
| Qwen3-VL-8B-InstructRAG Strategy=Direct (None)2026.02 | 27.56 | |
| Qwen3-VL-8B-Instruct OCR RAGRAG Strategy=OCR RAG2026.02 | 26.4 | |
| GLM-4.1V-9B-Thinking Embedding RAGRAG Strategy=Embedding RAG2026.02 | 26.29 |