Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Debate on MATH
Loading...
36.9
Accuracy
OPTIMA-iDPO SC
23.38
26.89
30.4
33.91
Oct 10, 2024
Accuracy
Token Count
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Token Count
OPTIMA-iDPO SC
optimization_strategy=...
2024.10
36.9
2,743.1
SC
n=8
2024.10
35.7
2,600.9
OPTIMA-iSFT-DPO SC
optimization_strategy=...
2024.10
34.8
2,788.5
OPTIMA-iSFT SC
optimization_strategy=...
2024.10
32.4
2,432.9
OPTIMA-iDPO
optimization_strategy=...
2024.10
30.4
272.8
OPTIMA-iSFT
optimization_strategy=...
2024.10
30.1
830.3
MAD
2024.10
29.8
1,517.6
OPTIMA-iSFT-DPO
optimization_strategy=...
2024.10
29.3
488.1
AutoForm
2024.10
26.1
644.3
CoT
2024.10
23.9
329.8
Feedback
Search any
task
Search any
task