| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | Anthropic | Closed | 66.2% | |
| 2 | GPT-5.5 | OpenAI | Closed | 54.1% | |
| 3 | GPT-5.4 | OpenAI | Closed | 53.2% | |
| 4 | MiniMax M3 | MiniMax | Open | 45.1% | |
| 5 | Claude Opus 4.7 (Adaptive) | Anthropic | Closed | 43.6% |
| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | Anthropic | Closed | 66.2% | |
| 2 | GPT-5.5 | OpenAI | Closed | 54.1% | |
| 3 | GPT-5.4 | OpenAI | Closed | 53.2% | |
| 4 | MiniMax M3 | MiniMax | Open | 45.1% | |
| 5 | Claude Opus 4.7 (Adaptive) | Anthropic | Closed | 43.6% |