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

Question Answering on LoCoMo Overall (BLEU-1, F1, LLM-as-a-Judge)

39.81BLEU-1

DeltaMem-4o-mini

24.220428.267732.31536.3623Apr 2, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.04
39.8150.3272.92
2026.04
39.7850.7275.13
2026.04
39.2950.1374.03
2026.04
37.7347.5170.13
2026.04
36.6347.2771.04
2026.04
34.1744.8166.43
2026.04
33.7942.5557.86
2026.04
33.6443.5765.99
2026.04
30.0636.8858.11
2026.04
26.0633.6462.34
2026.04
24.8229.9648.38