Summarization on eBay WebForm
4.325Mean Auto-Rating (r)Llama 3.1 8B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Llama 3.1 8BVersion=r12025.11 | 4.325 | 0.135 | |
| Llama 3.1 8BVersion=org2025.11 | 4.19 | — | |
| Qwen3 4BVersion=r12025.11 | 4.115 | 0.105 | |
| GPT3.5Version=out-of-box2025.11 | 4.03 | — | |
| Qwen3 4BVersion=org2025.11 | 4.01 | — | |
| Llama 3.1 8BVersion=r22025.11 | 4.005 | -0.185 | |
| Qwen3 4BVersion=out-of-box2025.11 | 3.975 | -0.035 | |
| Phi3.5mini 4BVersion=org2025.11 | 3.97 | — | |
| Phi3.5mini 4BVersion=r12025.11 | 3.96 | -0.01 | |
| Llama 3.2 1BVersion=r12025.11 | 3.905 | 0.125 | |
| Llama 3.2 3BVersion=r12025.11 | 3.885 | 0.88 | |
| Llama 3.2 3BVersion=r22025.11 | 3.875 | 0.87 | |
| Qwen3 4BVersion=r22025.11 | 3.835 | -0.175 | |
| Llama 3.2 1BVersion=org2025.11 | 3.78 | — | |
| Gemma3 1BVersion=org2025.11 | 3.78 | — | |
| Phi3.5mini 4BVersion=r22025.11 | 3.775 | -0.195 | |
| Llama 3.2 1BVersion=r22025.11 | 3.72 | -0.06 | |
| Llama 3.1 8BVersion=out-of-box2025.11 | 3.625 | -0.565 | |
| Gemma3 1BVersion=r22025.11 | 3.35 | -0.43 | |
| Phi3.5mini 4BVersion=out-of-box2025.11 | 3.08 | -0.89 | |
| Gemma3 270MVersion=org2025.11 | 3.055 | — | |
| Llama 3.2 3BVersion=org2025.11 | 3.005 | — | |
| Gemma3 1BVersion=r12025.11 | 3 | -0.78 | |
| Gemma3 270MVersion=r22025.11 | 2.895 | -0.16 | |
| Gemma3 270MVersion=r12025.11 | 2.675 | -0.38 | |
| Llama 3.2 3BVersion=out-of-box2025.11 | 2.425 | -0.58 | |
| Llama 3.2 1BVersion=out-of-box2025.11 | 1.625 | -2.155 | |
| Gemma3 1BVersion=out-of-box2025.11 | 1.32 | -2.46 | |
| Gemma3 270MVersion=out-of-box2025.11 | 1.18 | -1.875 |