Locomo
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
LoCoMo
86.46Recall@10
18
LoCoMo
76.7Accuracy (%)
18
LOCOMO single
68.62F1 Score
18
LOCOMO locomo_open
62.02F1 Score
18
LoCoMo (test)
27.56Multi-hop BLEU
18
LoCoMo (test)
72.3LLM Score (Temporal)
16
LoCoMo (test)
60.2Single Hop F1
15
LoCoMo
67.3Rubric Judge Accuracy
15
LOCOMO
71.6F1 Score
15
LoCoMo 10 conversations (full release)
35.2MultiHop F1
14
LoCoMo
43.94F1 Score
13
LoCoMo
94.37Score
13
LoCoMo Average scores
22.4F1 Score
12
LoCoMo (Adversarial)
4.94F1 Score
12
LoCoMo 3x
23.44F1 Score
12
LOCOMO Overall
88.32LLM Judge Score
12
LOCOMO Temporal
69.82F1 Score
12
LOCOMO Multi-hop
56.72F1 Score
12
LoCoMo
82.62Multi-Hop Accuracy
12
LoCoMo (test)
50.7F1 Score
12
LoCoMo Temporal 2024
62.68F1 Score
12
LoCoMo Open-Domain 2024
54.77F1 Score
12
LoCoMo Multi-Hop 2024
31.51F1 Score
12
LoCoMo Single-Hop 2024
48.66F1 Score
12
LoCoMo Overall
49.4F1 Score
12