Output Length Prediction on ForeLen Reasoning
111.23MAEEGTP
Evaluation Results
| Method | Links | |
|---|---|---|
| EGTPModel=Llama3.2 3B2026.02 | 111.23 | |
| TRAILModel=Qwen2.5 7B2026.02 | 124.19 | |
| TRAILModel=Qwen2.5 3B2026.02 | 132.2 | |
| EGTPModel=Qwen2.5 7B2026.02 | 133.57 | |
| LTR-CModel=Qwen2.5 7B2026.02 | 134.55 | |
| EGTPModel=Llama3.2 1B2026.02 | 138.04 | |
| EGTPModel=Qwen2.5 3B2026.02 | 139.04 | |
| LTR-CModel=Llama3.2 1B2026.02 | 142.28 | |
| SSJF-MCModel=Llama3.2 1B2026.02 | 143.78 | |
| LTR-CModel=Qwen2.5 3B2026.02 | 145.53 | |
| TRAILModel=Llama3.2 1B2026.02 | 148.28 | |
| S3Model=Llama3.2 1B2026.02 | 152.29 | |
| SSJF-RegModel=Llama3.2 1B2026.02 | 157.67 | |
| SSJF-MCModel=Llama3.2 3B2026.02 | 160.36 | |
| S3Model=Llama3.2 3B2026.02 | 164.22 | |
| S3Model=Qwen2.5 7B2026.02 | 168.8 | |
| S3Model=Qwen2.5 3B2026.02 | 169.72 | |
| LTR-CModel=Llama3.2 3B2026.02 | 174.01 | |
| TRAILModel=Llama3.2 3B2026.02 | 177.16 | |
| SSJF-RegModel=Llama3.2 3B2026.02 | 186.16 | |
| PiAModel=Llama3.2 1B2026.02 | 254.57 | |
| PiAModel=Llama3.2 3B2026.02 | 264.66 | |
| TPVModel=Llama3.2 1B2026.02 | 273.04 | |
| SSJF-RegModel=Qwen2.5 7B2026.02 | 298.8 | |
| SSJF-RegModel=Qwen2.5 3B2026.02 | 325.38 | |
| TPVModel=Llama3.2 3B2026.02 | 373.03 | |
| PiAModel=Qwen2.5 7B2026.02 | 412.84 | |
| PiAModel=Qwen2.5 3B2026.02 | 428.1 | |
| TPVModel=Qwen2.5 7B2026.02 | 466.56 | |
| TPVModel=Qwen2.5 3B2026.02 | 621.72 | |
| SSJF-MCModel=Qwen2.5 7B2026.02 | 770.92 | |
| SSJF-MCModel=Qwen2.5 3B2026.02 | 789.21 |