Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Instruction Following on IFEval (Acc_prompt)
Loading...
19.6
Accuracy (Prompt)
FiMi-RM
16.48
17.29
18.1
18.91
May 19, 2025
Accuracy (Prompt)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (Prompt)
FiMi-RM
Backbone=Gemma2-9B, Op...
2025.05
19.6
FiMi-RM
Backbone=Qwen2.5-7B, O...
2025.05
19
ODIN
Backbone=Qwen2.5-7B, O...
2025.05
18.6
Length Penalty
Backbone=Gemma2-9B, Op...
2025.05
18.2
Vanilla RM
Backbone=Gemma2-9B, Op...
2025.05
18
ODIN
Backbone=Gemma2-9B, Op...
2025.05
17.8
Vanilla RM
Backbone=Qwen2.5-7B, O...
2025.05
17.4
Length Penalty
Backbone=Qwen2.5-7B, O...
2025.05
16.6
Feedback
Search any
task
Search any
task