| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Sakana Fugu-Ultra | Sakana AI | Proprietary | 93.6% | |
| 2 | Qwen3.8 Max | Alibaba | Open weights | 92.9% | |
| 3 | Qwen3.7 Plus | Alibaba | Proprietary | 91.7% | |
| 4 | Qwen3.7 Max | Alibaba · Closed | 90.4% | ||
| 5 | Sakana Fugu | Sakana AI · Closed | 86.6% | ||
| 6 | Gemini 3.5 Flash | Google · Closed | 77.3% | ||
| 7 | Gemini 3.5 Flash-Lite | Google · Closed | 72.2% | ||
| 8 | Pokee-Isaac 28B | Pokee AI · Closed | 60.7% | ||
| 9 | Gemma 4 12B | Google · Open weight | 43.4% |