List your company

Output Length Prediction on ForeLen Reasoning

111.23MAEEGTP
84.1108267.1654450.22633.2746Feb 12, 2026

Evaluation results

MethodLinks
EGTPModel=Llama3.2 3B2026.02111.23
TRAILModel=Qwen2.5 7B2026.02124.19
TRAILModel=Qwen2.5 3B2026.02132.2
EGTPModel=Qwen2.5 7B2026.02133.57
LTR-CModel=Qwen2.5 7B2026.02134.55
EGTPModel=Llama3.2 1B2026.02138.04
EGTPModel=Qwen2.5 3B2026.02139.04
LTR-CModel=Llama3.2 1B2026.02142.28
SSJF-MCModel=Llama3.2 1B2026.02143.78
LTR-CModel=Qwen2.5 3B2026.02145.53
TRAILModel=Llama3.2 1B2026.02148.28
S3Model=Llama3.2 1B2026.02152.29
SSJF-RegModel=Llama3.2 1B2026.02157.67
SSJF-MCModel=Llama3.2 3B2026.02160.36
S3Model=Llama3.2 3B2026.02164.22
S3Model=Qwen2.5 7B2026.02168.8
S3Model=Qwen2.5 3B2026.02169.72
LTR-CModel=Llama3.2 3B2026.02174.01
TRAILModel=Llama3.2 3B2026.02177.16
SSJF-RegModel=Llama3.2 3B2026.02186.16
PiAModel=Llama3.2 1B2026.02254.57
PiAModel=Llama3.2 3B2026.02264.66
TPVModel=Llama3.2 1B2026.02273.04
SSJF-RegModel=Qwen2.5 7B2026.02298.8
SSJF-RegModel=Qwen2.5 3B2026.02325.38
TPVModel=Llama3.2 3B2026.02373.03
PiAModel=Qwen2.5 7B2026.02412.84
PiAModel=Qwen2.5 3B2026.02428.1
TPVModel=Qwen2.5 7B2026.02466.56
TPVModel=Qwen2.5 3B2026.02621.72
SSJF-MCModel=Qwen2.5 7B2026.02770.92
SSJF-MCModel=Qwen2.5 3B2026.02789.21