Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Instruction Following on MT-Bench short-context
Loading...
8.13
MT-Bench Score
officially post-trained
7.0796
7.3523
7.625
7.8977
Oct 28, 2024
MT-Bench Score
Updated 4d ago
Evaluation Results
Method
Method
Links
MT-Bench Score
officially post-trained
Backbone=Llama-3.1-8B
2024.10
8.13
officially post-trained
Backbone=GLM-4-9B
2024.10
8.09
DPO w/ SRM
Backbone=Llama-3.1-8B
2024.10
7.58
DPO w/ Contrast
Backbone=Llama-3.1-8B
2024.10
7.58
DPO w/ LongReward
Backbone=GLM-4-9B
2024.10
7.58
DPO w/ Contrast
Backbone=GLM-4-9B
2024.10
7.54
DPO w/ SRM
Backbone=GLM-4-9B
2024.10
7.5
SFT
Backbone=GLM-4-9B
2024.10
7.37
DPO w/ LongReward
Backbone=Llama-3.1-8B
2024.10
7.24
SFT
Backbone=Llama-3.1-8B
2024.10
7.12
Feedback
Search any
task
Search any
task