HotpotQA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
HotpotQA
63.09F1 Score
14
HotpotQA
0.601EM
14
HotpotQA
1Relative Cost
14
HotpotQA
0.603String-F1
14
HotpotQA
34ASR
14
HotpotQA 500 QA pairs
38.3Exact Match (EM)
14
HotpotQA 2018 Wikipedia dump (dev)
46.8Accuracy
14
HotpotQA
76.2GPT Accuracy
14
HotpotQA
55.49LLM Judge Score
14
HotpotQA in-domain (test)
60.4ACC_R
14
HotpotQA 500 samples (val)
34.4EM
14
HotpotQA
66.8Accuracy
14
HotpotQA (test)
69.4NDCG@10
14
HotpotQA
45.55Accuracy
13
HotpotQA
33.9OSR Score
13
HotpotQA
72.65Recall@2
13
HotpotQA (dev)
66.4Recall @ 2
13
HotpotQA distractor (dev)
89F1 Score
13
HotpotQA
100Moderation Guard Rate (OpenAI)
12
HotpotQA
46.1EM
12
HotpotQA
78.7F1 Score
12
HotpotQA
69.9F1 Score
12
HotpotQA
3.77Speedup Factor
12
HotpotQA
82Top-5 Accuracy
12
HotpotQA
47.9EM
12