| Rang | Vergleichen | Modell | Ergebnis |
|---|---|---|---|
| 101 |  Trinity Large Thinking Arcee AI | 40.6% | |
| 102 | 40.3% | ||
| 103 |  Mistral Medium 3.5 Mistral | 40.2% | |
| 104 | 40.0% | ||
| 105 |  K2 Horizon MoVA 36B A4B Institute of Foundation Models | 40.0% | |
| 106 |  Qwen3.8 27B (Low) Alibaba | 40.0% | |
| 107 | 39.9% | ||
| 108 | 39.7% | ||
| 109 | 39.7% | ||
| 110 | Qwen3.8 27B (Medium) Alibaba | 39.0% | |
| 111 |  gpt-oss-20b (High) OpenAI | 38.9% | |
| 112 | Mistral Small 4 (Reasoning) Mistral | 38.8% | |
| 113 |  North Mini Code Cohere | 38.8% | |
| 114 | Command A+ Cohere | 38.5% | |
| 115 | 38.5% | ||
| 116 |  Mercury 2.5 Inception | 38.5% | |
| 117 | 37.8% | ||
| 118 |  G9v3-39A5B AI9Stars | 36.8% | |
| 119 | Qwen3.6 35B A3B (Reasoning) Alibaba | 36.6% | |
| 120 |  LongCat 2.0 LongCat | 36.3% | |
| 121 | Qwen3.8 27B (Non-reasoning) Alibaba | 36.2% | |
| 122 | Qwen3 Coder Next Alibaba | 36.2% | |
| 123 | gpt-oss-120b (High) OpenAI | 34.0% | |
| 124 |  Nemotron 3.5 Lightning NVIDIA | 32.1% | |
| 125 |  Llama 4 Maverick Meta | 31.7% | |
| 126 | 31.5% | ||
| 127 | 30.6% | ||
| 128 | Qwen3.5 9B (Reasoning) Alibaba | 29.5% | |
| 129 | K2 Horizon 7B Institute of Foundation Models | 27.5% | |
| 130 |  MiniCPM5-2B OpenBMB | 26.3% | |
| 131 | 25.3% | ||
| 132 |  Gemma 4 E4B (Reasoning) Google | 24.4% | |
| 133 |  Ling 3.0 Tiny InclusionAI | 24.2% | |
| 134 | Ministral 3 14B Mistral | 23.8% | |
| 135 | K2 Horizon 3.7B Institute of Foundation Models | 22.0% | |
| 136 |  Celeris-1 Celeris | 21.6% | |
| 137 | Llama 4 Scout Meta | 21.3% | |
| 138 | Ministral 3 8B Mistral | 20.7% | |
| 139 | 16.1% | ||
| 140 | Ministral 3 3B Mistral | 15.3% | |
| 141 |  LFM2.5-2.6B Liquid AI | 14.4% | |
| 142 | K2 Horizon 0.9B Institute of Foundation Models | 6.9% |
