| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Gemini 3.1 Pro | Closed | 69.4% | ||
| 2 | GPT-5.4 | OpenAI | Closed | 65.4% | |
| 3 | Muse Spark | Meta | Closed | 64.7% | |
| 4 | Qwen3.6-27B | Alibaba | Open | 62.5% | |
| 5 | Grok 4.20 | xAI | Closed | 54.1% | |
| 6 | Claude Opus 4.6 | Anthropic | Closed | 51.6% |
| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Gemini 3.1 Pro | Closed | 69.4% | ||
| 2 | GPT-5.4 | OpenAI | Closed | 65.4% | |
| 3 | Muse Spark | Meta | Closed | 64.7% | |
| 4 | Qwen3.6-27B | Alibaba | Open | 62.5% | |
| 5 | Grok 4.20 | xAI | Closed | 54.1% | |
| 6 | Claude Opus 4.6 | Anthropic | Closed | 51.6% |