Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Open-ended Generation on NQ entity-swapped (test)
Loading...
73.73
Exact Match
HICD
55.4364
60.1857
64.935
69.6843
Mar 17, 2025
Exact Match
Updated 4d ago
Evaluation Results
Method
Method
Links
Exact Match
HICD
Backbone=Mistral-7B-v0.3
2025.03
73.73
CAD
Backbone=Mistral-7B-v0.3
2025.03
73.07
HICD
Backbone=LLaMA3-8B-Ins...
2025.03
72.64
CAD
Backbone=LLaMA3-8B-Ins...
2025.03
72.51
HICD
Backbone=LLaMA-7B
2025.03
69.61
CAD
Backbone=LLaMA-7B
2025.03
68.24
DoLA
Backbone=Mistral-7B-v0.3
2025.03
62.24
Mistral-7B-v0.3
Backbone=Mistral-7B-v0.3
2025.03
61.41
DoLA
Backbone=LLaMA3-8B-Ins...
2025.03
58.86
LLaMA3-8B-Instruct
Backbone=LLaMA3-8B-Ins...
2025.03
58.74
LLaMA-7B
Backbone=LLaMA-7B
2025.03
56.25
DoLA
Backbone=LLaMA-7B
2025.03
56.14
Feedback
Search any
task
Search any
task