List your company

Recognizing Textual Entailment on RTE

26.24Delta 1Llama2-13B
-0.58166.381713.34520.3083Nov 24, 2025

Evaluation results

MethodLinks
Llama2-13Bscenario=original dataset2025.1126.249.02
Llama2-13Bscenario=semantic dataset2025.1122.632.15
Llama2-13Bscenario=updated dataset (ours)2025.1121.121.1
Llama3-8Bscenario=original dataset2025.1120.888.79
Yi1.5-6Bscenario=original dataset2025.1119.648.8
Ministral-8Bscenario=original dataset2025.1117.086.64
Mistral-12Bscenario=original dataset2025.1113.437.49
Llama3-8Bscenario=semantic dataset2025.1112.20.12
Yi1.5-6Bscenario=semantic dataset2025.1111.160.36
Yi1.5-9Bscenario=original dataset2025.119.218.08
Qwen2.5-14Bscenario=original dataset2025.117.215.43
Qwen2.5-7Bscenario=original dataset2025.117.086.03
Yi1.5-6Bscenario=updated dataset (ours)2025.116.761.69
Ministral-8Bscenario=semantic dataset2025.116.5-0.72
Qwen2.5-14Bscenario=updated dataset (ours)2025.114.380
Llama3-8Bscenario=updated dataset (ours)2025.114.210.13
Ministral-8Bscenario=updated dataset (ours)2025.114.03-1.46
Mistral-12Bscenario=semantic dataset2025.112.740.11
Yi1.5-9Bscenario=semantic dataset2025.112.531.71
Qwen2.5-7Bscenario=updated dataset (ours)2025.112.311.08
Qwen2.5-7Bscenario=semantic dataset2025.111.740.72
Mistral-12Bscenario=updated dataset (ours)2025.111.45-0.62
Qwen2.5-14Bscenario=semantic dataset2025.110.520.12
Yi1.5-9Bscenario=updated dataset (ours)2025.110.45-0.37