| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | MAI-Thinking-1 | Microsoft | Proprietary | 97% | |
| 2 | Kimi K2.5 | Moonshot AI | Open weights | 96.1% | |
| 3 | Kimi K2.5 (Reasoning) | Moonshot AI | Proprietary | 96.1% | |
| 4 | GLM-4.7 | Z.AI · Open weight | 95.7% | ||
| 5 | Ternary Bonsai 2 27B | Prism ML · Open weight | 95% | ||
| 6 | MiMo-V2-Flash | Xiaomi · Open weight | 94.1% | ||
| 7 | Mercury 2 | Inception · Closed | 91.1% | ||
| 8 | Granite 4.2 30B | IBM · Open weight | 89.2% | ||
| 9 | Claude Sonnet 4.5 | Anthropic · Closed | 87% | ||
| 10 | Granite 4.2 8B | IBM · Open weight | 86.7% | ||
| 11 | MiniCPM5-2B | OpenBMB · Open weight | 86.5% | ||
| 12 | Exaone 4.0 32B | LG AI Research · Open weight | 85.3% | ||
| 13 | GPT-5 nano | OpenAI · Closed | 85.2% | ||
| 14 | Nemotron 3 Nano Omni 30B A3B | NVIDIA · Open weight | 82.1% | ||
| 15 | Granite 4.2 3B | IBM · Open weight | 78.3% | ||
| 16 | LFM2.5-2.6B | LiquidAI · Open weight | 51.9% | ||
| 17 | LFM2.5-8B-A1B | LiquidAI · Open weight | 42.5% | ||
| 18 | MiniCPM5-1B | OpenBMB · Open weight | 40.4% |