Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Output Length Prediction on LMSYS
Loading...
68.33
MAE
EGTP
57.468
130.7865
204.105
277.4235
Feb 12, 2026
MAE
Updated 4d ago
Evaluation Results
Method
Method
Links
MAE
EGTP
Model=Claude-2
2026.02
68.33
LTR-C
Model=Claude-2
2026.02
77.03
S3
Model=Claude-2
2026.02
83.51
EGTP
Model=GPT-4
2026.02
87.32
PiA
Model=Claude-2
2026.02
91.32
S3
Model=GPT-4
2026.02
96.03
TRAIL
Model=Claude-2
2026.02
102.39
LTR-C
Model=GPT-4
2026.02
104.11
TRAIL
Model=GPT-4
2026.02
116.91
SSJF-MC
Model=Claude-2
2026.02
140.18
PiA
Model=GPT-4
2026.02
143.02
SSJF-Reg
Model=Claude-2
2026.02
152
SSJF-Reg
Model=GPT-4
2026.02
171.62
SSJF-MC
Model=GPT-4
2026.02
190.93
TPV
Model=Claude-2
2026.02
283.81
TPV
Model=GPT-4
2026.02
339.88
Feedback
Search any
task
Search any
task