Creativity Context Generation on CreaTE
81.28CoherenceAlphaContext
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| AlphaContext2026.04 | 81.28 | 79.06 | 79.93 | 71.06 | 75.49 | 80.3 | 96.06 | |
| Gemini-3.0-Pro-PreviewCategory=General-purpose LLMs2026.04 | 72.54 | 75.37 | 62.56 | 48.4 | 64.16 | 63.3 | 91.81 | |
| GPT-5.1Category=General-purpose LLMs2026.04 | 70.44 | 70.2 | 65.39 | 50.37 | 71.8 | 68.6 | 92.88 | |
| SS-GENCategory=Structured generation frameworks2026.04 | 60.22 | 69.69 | 56.4 | 60.1 | 51.85 | 53.57 | 90.24 | |
| CRITICSCategory=Structured generation frameworks2026.04 | 51.11 | 61.95 | 61.21 | 37.81 | 54.43 | 42.12 | 92.31 | |
| DeepSeek-V3.1Category=General-purpose LLMs2026.04 | 50 | 50 | 50 | 50 | 50 | 50 | 94.33 | |
| DOC-v2Category=Structured generation frameworks2026.04 | 49.14 | 61.33 | 61.82 | 34.98 | 51.11 | 43.1 | 92.82 | |
| Qwen3-235B-A22BCategory=General-purpose LLMs2026.04 | 41.5 | 47.91 | 45.07 | 33.87 | 46.55 | 53.33 | 92.09 | |
| LongWriter-glm4-9bCategory=Long-form specialized LLMs2026.04 | 32.27 | 31.4 | 31.38 | 36.19 | 32.98 | 31.32 | 88.69 | |
| Llama3.3-70B-InstructCategory=General-purpose LLMs2026.04 | 27.83 | 26.97 | 33.99 | 27.46 | 30.54 | 20.07 | 90.39 | |
| LongWriter-llama3.1-8bCategory=Long-form specialized LLMs2026.04 | 26.6 | 27.46 | 28.63 | 23.4 | 33.62 | 25.99 | 91.18 |