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

Long-context Question Answering on 2WikiMQA Fixed Chunk 2048

52.53QA Score

Baseline

38.95842.481546.00549.5285Mar 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
52.53
2026.03
51.76
2026.03
51.61
2026.03
50.89
2026.03
50.64
2026.03
47.73
2026.03
46.35
2026.03
45.88
2026.03
44.55
2026.03
44.17
2026.03
44.01
2026.03
43.7
2026.03
43.21
2026.03
42.26
2026.03
41.31
2026.03
40.87
2026.03
39.69
2026.03
39.48