Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Key-Value Recall
Loading...
47.5
LAMA Recall
REMIX
-1.796
11.002
23.8
36.598
Nov 11, 2024
LAMA Recall
EntityQA Recall
WebQA Recall
Factoid Avg Recall
GSM8K Accuracy
MATH Accuracy
EvolCode Pass Rate
APPS Pass Rate
UltraChat Score
Non-Factoid Avg Recall
Updated 27d ago
Evaluation Results
Method
Method
Links
LAMA Recall
EntityQA Recall
WebQA Recall
Factoid Avg Recall
GSM8K Accuracy
MATH Accuracy
EvolCode Pass Rate
APPS Pass Rate
UltraChat Score
Non-Factoid Avg Recall
REMIX
Model=Mistral-7B-v0.3,...
2024.11
47.5
44.1
39
43.5
60.1
39.1
52.9
54.8
81
57
No Mixing
Model=Mistral-7B-v0.3,...
2024.11
0.1
15.4
29.6
15
4.8
1.5
12.7
13.1
51.9
16.8
Feedback
Search any
task
Search any
task
