| ์์ | ๋น๊ต | ๋ชจ๋ธ | ์ ์ |
|---|---|---|---|
| 51 |  Qwen3.5 0.8B (Non-reasoning) Alibaba | 65.2% | |
| 52 |  HyperNova 60B 2605 (High, Based on gpt-oss-120b) Multiverse Computing | 63.2% | |
| 53 | 62.0% | ||
| 54 |  gpt-oss-20b (High) OpenAI | 60.2% | |
| 55 |  Gemma 4 31B (Reasoning) Google | 59.9% | |
| 56 |  Doubao Seed Code ByteDance Seed | 58.2% | |
| 57 | 53.2% | ||
| 58 |  Magistral Medium 1.2 Mistral | 52.0% | |
| 59 | gpt-oss-20b (Low) OpenAI | 50.3% | |
| 60 |  Solar Open 100B (Reasoning) Upstage | 48.2% | |
| 61 | Qwen3.5 0.8B (Reasoning) Alibaba | 47.7% | |
| 62 |  Sarvam 105B (High) Sarvam | 46.8% | |
| 63 |  Motif-2-12.7B-Reasoning Motif Technologies | 46.5% | |
| 64 | 45.3% | ||
| 65 | gpt-oss-120b (Low) OpenAI | 45.0% | |
| 66 | 44.7% | ||
| 67 | 43.6% | ||
| 68 | 41.5% | ||
| 69 | Mistral Small 4 (Reasoning) Mistral | 41.2% | |
| 70 | 40.9% | ||
| 71 | 40.4% | ||
| 72 |  Nova Premier Amazon | 38.3% | |
| 73 |  North Mini Code Cohere | 37.4% | |
| 74 | Gemma 4 12B (Reasoning) Google | 36.3% | |
| 75 | Sarvam 30B (High) Sarvam | 34.5% | |
| 76 | 31.9% | ||
| 77 | 28.1% | ||
| 78 |  Falcon-H1R-7B TII UAE | 27.8% | |
| 79 |  K2-V2 (High) Institute of Foundation Models | 27.8% | |
| 80 | Magistral Small 1.2 Mistral | 27.8% | |
| 81 | Ministral 3 14B Mistral | 27.2% | |
| 82 |  Hermes 4 - Llama-3.1 405B (Non-reasoning) Nous Research | 26.6% | |
| 83 |  INTELLECT-3 (Based on GLM-4.5-Air) Prime Intellect | 26.6% | |
| 84 | 26.6% | ||
| 85 | Ministral 3 8B Mistral | 26.6% | |
| 86 | 26.0% | ||
| 87 | K2 Think V2 Institute of Foundation Models | 25.4% | |
| 88 | 25.4% | ||
| 89 | K2-V2 (Medium) Institute of Foundation Models | 24.9% | |
| 90 | Ministral 3 3B Mistral | 24.9% | |
| 91 | 23.4% | ||
| 92 | Hermes 4 - Llama-3.1 70B (Reasoning) Nous Research | 22.5% | |
| 93 | 22.2% | ||
| 94 | Hermes 4 - Llama-3.1 405B (Reasoning) Nous Research | 22.2% | |
| 95 | 21.9% | ||
| 96 | Hermes 4 - Llama-3.1 70B (Non-reasoning) Nous Research | 21.6% | |
| 97 |  Nanbeige4.1-3B Nanbeige | 21.6% | |
| 98 | Qwen3 Next 80B A3B Instruct Alibaba | 21.6% | |
| 99 | 21.3% | ||
| 100 |  Olmo 3.1 32B Instruct Allen Institute for AI | 21.3% |
