| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 | Anthropic | Closed | claude-opus-5 | |
| 2 | Kimi K3 | Moonshot AI | Closed | kimi-3 | |
| 3 | Claude Opus 4.8 | Anthropic | Closed | claude-opus-4-8 | |
| 4 | Step 3.7 Flash | StepFun · Open weight | 92.8% | ||
| 5 | Kimi K2.6 | Moonshot AI · Open weight | 92.5% | ||
| 6 | Muse Spark 1.1 | Meta · Closed | 84.9% | ||
| 7 | Kimi K2.5 | Moonshot AI · Open weight | 77.1% | ||
| 8 | Muse Spark | Meta · Closed | 74.8% | ||
| 9 | Claude Opus 4.6 | Anthropic · Closed | 73.7% | ||
| 10 | GPT-5.4 | OpenAI · Closed | 73.6% | ||
| 11 | Gemini 3.1 Pro | Google · Closed | 69.7% | ||
| 12 | Grok 4.20 | xAI · Closed | 62.8% |