Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Completion Length Prediction on GSM8K (eval)
Loading...
42.29
MAE
Completion Length Probe
39.3348
59.2824
79.23
99.1776
Jul 6, 2026
MAE
Updated 19d ago
Evaluation Results
Method
Method
Links
MAE
Completion Length Probe
Model=Llama-3.1-8B
2026.07
42.29
Statistical baseline
Model=Llama-3.1-8B
2026.07
58.66
Completion Length Probe
Model=Mistral-7B
2026.07
74.92
Completion Length Probe
Model=Olmo-3-7B
2026.07
80.46
Statistical baseline
Model=Mistral-7B
2026.07
84.81
Statistical baseline
Model=Olmo-3-7B
2026.07
116.17
Feedback
Search any
task
Search any
task