Story Generation on Story
8.36DiversityAnnotated
Evaluation results
| Method | Links | ||
|---|---|---|---|
| AnnotatedNumber of Parameters=2.5B, Temperature=0.9, Evaluation Judge=GPT-5.42026.05 | 8.36 | — | |
| AnnotatedNumber of Parameters=2.5B, Temperature=1.0, Evaluation Judge=GPT-5.42026.05 | 8.1 | — | |
| StandardNumber of Parameters=2.5B, Temperature=1.0, Evaluation Judge=GPT-5.42026.05 | 7.39 | — | |
| AnnotatedNumber of Parameters=2.5B, Temperature=1.05, Evaluation Judge=GPT-5.42026.05 | 7.39 | — | |
| AnnotatedNumber of Parameters=2.5B, Temperature=0.6, Evaluation Judge=GPT-5.42026.05 | 7.13 | — | |
| StandardNumber of Parameters=2.5B, Temperature=1.05, Evaluation Judge=GPT-5.42026.05 | 6.94 | — | |
| StandardNumber of Parameters=2.5B, Temperature=0.9, Evaluation Judge=GPT-5.42026.05 | 6.88 | — | |
| AnnotatedNumber of Parameters=2.5B, Temperature=1.1, Evaluation Judge=GPT-5.42026.05 | 6.8 | — | |
| StandardNumber of Parameters=2.5B, Temperature=1.1, Evaluation Judge=GPT-5.42026.05 | 6.41 | — | |
| StandardNumber of Parameters=2.5B, Temperature=0.6, Evaluation Judge=GPT-5.42026.05 | 5.07 | — | |
| SLRBackbone=Llama2026.02 | 0.366 | 90.8 | |
| SLRBackbone=Gemma2026.02 | 0.364 | 117.7 | |
| Proxy-SoupBackbone=Gemma2026.02 | 0.326 | 117.5 | |
| Proxy-SoupBackbone=Llama2026.02 | 0.297 | 87.8 | |
| Post-trainedBackbone=Gemma2026.02 | 0.294 | 122.6 | |
| Post-trainedBackbone=Llama2026.02 | 0.274 | 93.4 | |
| SLRBackbone=Qwen2026.02 | 0.19 | 93.8 | |
| Proxy-SoupBackbone=Qwen2026.02 | 0.179 | 80.4 | |
| Post-trainedBackbone=Qwen2026.02 | 0.152 | 94.7 |