Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Output Length Prediction on LMSYS-Chat-1M (test)
Loading...
45.71
MAE
Noise Radius
36.4876
98.7388
160.99
223.2412
Apr 9, 2026
MAE
Updated 9d ago
Evaluation Results
Method
Method
Links
MAE
Noise Radius
Served Model=Llama-3-8B
2026.04
45.71
Noise Radius
Served Model=Qwen-2.5-7B
2026.04
56.05
ProD-D
Served Model=Llama-3-8B
2026.04
93.39
ProD-M
Served Model=Llama-3-8B
2026.04
94.59
TRAIL-last
Served Model=Llama-3-8B
2026.04
95.03
ProD-D
Served Model=Qwen-2.5-7B
2026.04
113.6
TRAIL-mean
Served Model=Llama-3-8B
2026.04
116.84
ProD-M
Served Model=Qwen-2.5-7B
2026.04
124.53
TRAIL-last
Served Model=Qwen-2.5-7B
2026.04
127.47
S^3
Served Model=Llama-3-8B
2026.04
142.28
TRAIL-mean
Served Model=Qwen-2.5-7B
2026.04
143.5
EGTP
Served Model=Llama-3-8B
2026.04
148.08
S^3
Served Model=Qwen-2.5-7B
2026.04
185.84
Constant Median
Served Model=Llama-3-8B
2026.04
213.31
Constant Median
Served Model=Qwen-2.5-7B
2026.04
264.9
EGTP
Served Model=Qwen-2.5-7B
2026.04
276.27
Feedback
Search any
task
Search any
task