Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Feedback Evaluation Alignment on MT Bench
Loading...
0.494
Kendall's Tau
TRACT
0.13624
0.22912
0.322
0.41488
Mar 6, 2025
Kendall's Tau
Updated 4d ago
Evaluation Results
Method
Method
Links
Kendall's Tau
TRACT
CoT=true, Train=C-RAFT...
2025.03
0.494
RAFT
CoT=false, Train=RAFT,...
2025.03
0.455
CE
CoT=false, Train=CE, D...
2025.03
0.429
RAIL
CoT=false, Train=None,...
2025.03
0.398
Prometheus-2-7B
CoT=true, Training obj...
2025.03
0.392
TRACT
CoT=true, Training obj...
2025.03
0.386
Mistral-7B-Instruct + CE (GPT-4 CoT)
CoT=true, Training obj...
2025.03
0.38
CE
CoT=true, Train=CE, Da...
2025.03
0.372
Mistral-7B-Instruct + RAFT
CoT=false, Training ob...
2025.03
0.342
Mistral-7B-Instruct + CE (GPT-4 Score)
CoT=false, Training ob...
2025.03
0.211
Mistral-7B-Instruct + RAIL Baseline
CoT=false, Inference m...
2025.03
0.15
Feedback
Search any
task
Search any
task