| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | GPT-5.4 | OpenAI | Proprietary | 41.0% | |
| 2 | Muse Spark | Meta | Proprietary | 33.0% | |
| 3 | Gemini 3.1 Pro | Proprietary | 29.0% | ||
| 4 | Qwen3.8 Max | Alibaba · Open weight | 24.0% | ||
| 5 | Kimi K3 | Moonshot AI · Closed | 23.0% | ||
| 6 | dots3-note Preview | Dots Studio · Open weight | 19.0% | ||
| 7 | Seed 2.1 Pro | ByteDance · Closed | 18.0% | ||
| 8 | Seed 2.1 Turbo | ByteDance · Closed | 11.0% |