Share your thoughts, 1 month free Claude Pro on usSee more

Long-context Question Answering on Qasper (Extract/Abstract/Bool F1)

54.57Extract F1

GLM-4.1V-9B-Thinking VERA

Updated 1mo ago

Evaluation Results

Method	Links
GLM-4.1V-9B-Thinking VERA 2026.02		54.57	34.67	94.23
GLM-4.1V-9B-Thinking ColPali RAG 2026.02		47.51	26.74	75.16
GLM-4.1V-9B-Thinking Random RAG 2026.02		46.92	29.61	80.47
GLM-4.1V-9B-Thinking Embedding RAG 2026.02		45.21	23.71	73.6
GLM-4.1V-9B-Thinking 2026.02		41.69	26.71	81.28
Qwen3-VL-8B-Instruct VERA 2026.02		39.29	22.56	71.12
Glyph 2026.02		39.26	24.45	45.62
Qwen3-VL-8B-Instruct 2026.02		25.54	17.82	70.36
Qwen3-VL-8B-Instruct OCR RAG 2026.02		25.15	17.99	71.48
Qwen3-VL-8B-Instruct Random RAG 2026.02		23.96	16.24	65.86