Creative Writing on AB-W
7.24ScoreGemini-2.5-pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-2.5-proCategory=Proprietary LLMs2026.06 | 7.24 | |
| Gemini-2.5-pro2026.06 | 7.24 | |
| Qwen3-8B-OPERACategory=Our Methods, Technique=OPERA2026.06 | 7.13 | |
| OPERABackbone=Qwen3-8B2026.06 | 7.13 | |
| Qwen3-8B-SFTCategory=Our Methods2026.06 | 7 | |
| Qwen3-8B-SFTMode=SFT2026.06 | 7 | |
| LongWriter-Zero-32BCategory=Open-source LLMs2026.06 | 6.95 | |
| LongWriter-Zero-32B2026.06 | 6.95 | |
| MiniMax-M2.5Category=Proprietary LLMs2026.06 | 6.84 | |
| MiniMax-M2.52026.06 | 6.84 | |
| Qwen3-8BCategory=Our Methods2026.06 | 6.64 | |
| Qwen3-8B2026.06 | 6.64 | |
| DeepWriter-8BCategory=Open-source LLMs2026.06 | 6.63 | |
| DeepWriter-8B2026.06 | 6.63 | |
| GPT-4o-0513Category=Proprietary LLMs2026.06 | 6.37 | |
| GPT-4o-05132026.06 | 6.37 | |
| Llama3.1-8B-OPERACategory=Our Methods, Technique=OPERA2026.06 | 6.15 | |
| OPERABackbone=Llama3.1-8B2026.06 | 6.15 | |
| Llama3.1-8B-SFTCategory=Our Methods2026.06 | 5.89 | |
| Llama3.1-8B-SFTMode=SFT2026.06 | 5.89 | |
| Llama3.1-8BCategory=Our Methods2026.06 | 5.15 | |
| Llama3.1-8B2026.06 | 5.15 | |
| LongWriter-8BCategory=Open-source LLMs2026.06 | 4.67 | |
| LongWriter-8B2026.06 | 4.67 |