| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Gemini 3.1 Pro | Closed | 81.3% | ||
| 2 | Muse Spark | Meta | Closed | 78.4% | |
| 3 | GPT-5.4 | OpenAI | Closed | 77.1% | |
| 4 | Grok 4.20 | xAI | Closed | 65.8% | |
| 5 | Claude Opus 4.6 | Anthropic | Closed | 64.8% |
| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Gemini 3.1 Pro | Closed | 81.3% | ||
| 2 | Muse Spark | Meta | Closed | 78.4% | |
| 3 | GPT-5.4 | OpenAI | Closed | 77.1% | |
| 4 | Grok 4.20 | xAI | Closed | 65.8% | |
| 5 | Claude Opus 4.6 | Anthropic | Closed | 64.8% |