Question-based Generation on CoMM validated (test)
7.35Style ScoreSEED-Llama
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| SEED-LlamaModel size=8B2026.03 | 7.35 | 5 | 3.85 | 5.07 | 5.21 | 2.57 | |
| Narrative Weaver2026.03 | 7.1 | 6.49 | 6.67 | 7.14 | 6.54 | 2.77 | |
| SEED-LlamaModel size=14B2026.03 | 7 | 6.28 | 5.71 | 6.02 | 5.85 | 3.28 | |
| MiniGPT-52026.03 | 6.62 | 5.96 | 5.83 | 6.26 | 5.67 | 2.73 | |
| Qwen2.5-VL + Flux.1-Dev2026.03 | 5.39 | 4.89 | 4.69 | 4.79 | 4.73 | 2.98 |