| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Qwen3.5 397B | Alibaba | Open | 59.1% | |
| 2 | Qwen3.7 Max | Alibaba | Closed | 59.0% | |
| 3 | Qwen3.6 Plus | Alibaba | Closed | 57.9% | |
| 4 | Claude Opus 4.5 | Anthropic | Closed | 56.7% | |
| 5 | Kimi K2.5 | Moonshot AI | Open | 56.0% | |
| 6 | GLM-5 | Z.AI | Open | 55.1% |
| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Qwen3.5 397B | Alibaba | Open | 59.1% | |
| 2 | Qwen3.7 Max | Alibaba | Closed | 59.0% | |
| 3 | Qwen3.6 Plus | Alibaba | Closed | 57.9% | |
| 4 | Claude Opus 4.5 | Anthropic | Closed | 56.7% | |
| 5 | Kimi K2.5 | Moonshot AI | Open | 56.0% | |
| 6 | GLM-5 | Z.AI | Open | 55.1% |