Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Output Length Prediction on LongBench (test)
Loading...
37.68
MAE
ProD-D
33.3428
62.6189
91.895
121.1711
Apr 9, 2026
MAE
Updated 9d ago
Evaluation Results
Method
Method
Links
MAE
ProD-D
Served Model=Llama-3-8B
2026.04
37.68
ProD-M
Served Model=Llama-3-8B
2026.04
38.13
TRAIL-last
Served Model=Llama-3-8B
2026.04
41.04
EGTP
Served Model=Llama-3-8B
2026.04
46.73
S^3
Served Model=Llama-3-8B
2026.04
50.01
TRAIL-mean
Served Model=Llama-3-8B
2026.04
50.99
ProD-D
Served Model=Qwen-2.5-7B
2026.04
51.41
ProD-M
Served Model=Qwen-2.5-7B
2026.04
55.54
Noise Radius
Served Model=Llama-3-8B
2026.04
56.38
Noise Radius
Served Model=Qwen-2.5-7B
2026.04
57.18
TRAIL-last
Served Model=Qwen-2.5-7B
2026.04
57.68
EGTP
Served Model=Qwen-2.5-7B
2026.04
69.84
S^3
Served Model=Qwen-2.5-7B
2026.04
72.21
TRAIL-mean
Served Model=Qwen-2.5-7B
2026.04
72.7
Constant Median
Served Model=Llama-3-8B
2026.04
95.69
Constant Median
Served Model=Qwen-2.5-7B
2026.04
146.11
Feedback
Search any
task
Search any
task