| Rang | Vergleichen | Modell | Ergebnis | Kosten / Aufgabe | Zeit / Aufgabe | Output-Tokens / Aufgabe |
|---|---|---|---|---|---|---|
| 101 |  K2 Horizon 375B A23B Institute of Foundation Models | 7.4% | $0 | 47.4s | 8.92K | |
| 102 |  Solar Pro 4 Upstage | 7.0% | — | — | — | |
| 103 |  Qwen3.5 9B (Reasoning) Alibaba | 6.6% | — | — | — | |
| 104 | Qwen3.6 35B A3B (Reasoning) Alibaba | 6.6% | — | — | — | |
| 105 |  A.X-K2 SK Telecom | 6.4% | — | — | — | |
| 106 |  LongCat 2.0 LongCat | 6.4% | — | — | — | |
| 107 |  Gemma 4 31B (Reasoning) Google | 6.0% | — | — | — | |
| 108 | 5.8% | $0.017 | 8.4s | 761 | ||
| 109 |  Ling-3.0-flash-Fin InclusionAI | 5.4% | — | — | — | |
| 110 |  Quasar 438B (Max, Based on GLM-5.2) Multiverse Computing | 5.4% | — | — | — | |
| 111 |  Motif 3 Motif Technologies | 5.2% | — | — | — | |
| 112 | Qwen3.8 27B (Non-reasoning) Alibaba | 5.2% | $0.069 | 32.8s | 1.33K | |
| 113 | 5.0% | $0.031 | 16.4s | 3.11K | ||
| 114 | Solar Mini 4 Upstage | 5.0% | — | — | — | |
| 115 | 4.4% | $0.024 | 7.3s | 914 | ||
| 116 |  gpt-oss-120b (High) OpenAI | 4.2% | $0.0093 | 47.5s | 7.68K | |
| 117 |  K-EXAONE 2.0 LG AI Research | 4.2% | — | — | 4.65K | |
| 118 | K2 Horizon MoVA 36B A4B Institute of Foundation Models | 4.2% | — | — | — | |
| 119 | Ring-2.6-1T InclusionAI | 3.8% | — | — | — | |
| 120 | 3.6% | $0.048 | 15.0s | 996 | ||
| 121 |  Mercury 2.5 Inception | 3.6% | — | — | — | |
| 122 | 3.4% | — | — | — | ||
| 123 | K2 Horizon 3.7B Institute of Foundation Models | 3.2% | — | — | — | |
| 124 | K2 Horizon 7B Institute of Foundation Models | 3.2% | — | — | — | |
| 125 |  Nemotron 3.5 Lightning NVIDIA | 3.0% | $0.005 | 56.4s | 13.7K | |
| 126 |  Mistral Medium 3.5 Mistral | 2.8% | $0.14 | 53.4s | 7.48K | |
| 127 | 2.8% | — | — | — | ||
| 128 | Qwen3 Coder Next Alibaba | 2.6% | — | — | — | |
| 129 | gpt-oss-20b (High) OpenAI | 2.0% | — | — | — | |
| 130 | 1.8% | — | — | — | ||
| 131 |  North Mini Code Cohere | 1.8% | $0 | 51.7s | 8.77K | |
| 132 |  MiniCPM5-2B OpenBMB | 1.4% | — | — | — | |
| 133 |  Celeris-1 Celeris | 1.2% | — | — | — | |
| 134 | Ministral 3 14B Mistral | 1.2% | — | — | — | |
| 135 |  Trinity Large Thinking Arcee AI | 1.2% | — | — | — | |
| 136 | Command A+ Cohere | 1.0% | $0 | 1m 3s | 12.5K | |
| 137 | Gemma 4 E4B (Reasoning) Google | 1.0% | — | — | — | |
| 138 | 1.0% | — | — | — | ||
| 139 | K2 Horizon 0.9B Institute of Foundation Models | 0.8% | — | — | — | |
| 140 | Ling 3.0 Tiny InclusionAI | 0.8% | — | — | — | |
| 141 |  Llama 4 Maverick Meta | 0.8% | — | — | — | |
| 142 | Ministral 3 8B Mistral | 0.8% | — | — | — | |
| 143 | 0.6% | $0.003 | 1m 19s | 7.64K | ||
| 144 | 0.4% | — | — | 4.1K | ||
| 145 | 0.2% | — | — | 7.66K | ||
| 146 | Llama 4 Scout Meta | 0.0% | — | — | — | |
| 147 | Ministral 3 3B Mistral | 0.0% | — | — | — | |
| 148 | Mistral Small 4 (Reasoning) Mistral | 0.0% | $0.0026 | 7.8s | 1.13K |
