Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Arithmetic Reasoning on SingleEq (test)
Loading...
0.971
Accuracy
DoRA + MoDEK
0.47284
0.60217
0.7315
0.86083
Oct 28, 2022
Feb 24, 2023
Jun 24, 2023
Oct 22, 2023
Feb 19, 2024
Jun 18, 2024
Oct 16, 2024
Accuracy
Updated 29d ago
Evaluation Results
Method
Method
Links
Accuracy
DoRA + MoDEK
Backbone=LLaMA3-8B
2024.10
0.971
DoRA
Backbone=LLaMA3-8B
2024.10
0.969
LoRAALL + MoDEK
Backbone=LLaMA3-8B
2024.10
0.965
LoRAALL
Backbone=LLaMA3-8B
2024.10
0.963
LoRA¬K + MoDEK (+0.04%)
Backbone=LLaMA3-8B
2024.10
0.96
LoRA¬K
Backbone=LLaMA3-8B
2024.10
0.957
REFT
Backbone=LLaMA3-8B
2024.10
0.94
CoRe
Backbone=GPT-J 12B, Ev...
2022.10
0.795
UNITDEP
Evaluation Protocol=Fi...
2022.10
0.723
DoRA + MoDEK
Backbone=LLaMA2-7B
2024.10
0.676
DoRA
Backbone=LLaMA2-7B
2024.10
0.674
LoRAALL + MoDEK
Backbone=LLaMA2-7B
2024.10
0.673
LoRAALL
Backbone=LLaMA2-7B
2024.10
0.669
LoRA¬K + MoDEK (+0.04%)
Backbone=LLaMA2-7B
2024.10
0.668
LoRA¬K
Backbone=LLaMA2-7B
2024.10
0.661
REFT
Backbone=LLaMA2-7B
2024.10
0.638
Self-Consistency
Backbone=GPT-J 6B, Eva...
2022.10
0.602
Generator only
Backbone=GPT-J 6B, Eva...
2022.10
0.492
Feedback
Search any
task
Search any
task