Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Single-hop Question Answering on Factrecall en
Loading...
31.36
Score
LM-infinite
1.1272
8.9761
16.825
24.6739
Jun 1, 2025
Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Score
LM-infinite
Backbone=Mistral-7B-In...
2025.06
31.36
DCS
Backbone=Llama-3-8B-In...
2025.06
29.89
Streaming
Backbone=Mistral-7B-In...
2025.06
29.64
DCS
Backbone=Vicuna-7B
2025.06
27.26
InfLLM
Backbone=Mistral-7B-In...
2025.06
24.64
InfLLM
Backbone=Llama-3-8B-In...
2025.06
19.22
InfLLM
Backbone=Vicuna-7B
2025.06
16.65
Llama-3-8B-Instruct
Backbone=Llama-3-8B-In...
2025.06
15.5
Streaming
Backbone=Llama-3-8B-In...
2025.06
12.36
LM-infinite
Backbone=Llama-3-8B-In...
2025.06
12.16
MOICE
Backbone=Vicuna-7B
2025.06
8.27
Vicuna-7B
Backbone=Vicuna-7B, Co...
2025.06
6.81
DCS
Backbone=Mistral-7B-In...
2025.06
6.64
LM-Infinite
Backbone=Vicuna-7B
2025.06
3.3
Streaming
Backbone=Vicuna-7B
2025.06
2.74
MOICE
Backbone=Mistral-7B-In...
2025.06
2.64
Mistral-7B-Instruct
Backbone=Mistral-7B-In...
2025.06
2.29
Feedback
Search any
task
Search any
task