HyperAI
Command Palette
Search for a command to run...
SciCode
معيار برمجي منتقى من قبل علماء يضم 288 مسألة فرعية في مجموعة الاختبار من 80 مسألة مخبرية عبر 16 تخصصًا علميًا.
- النماذج
- 142 الحالي، 251 إجمالاً
- الوسيط
- 48.7%
- المدى
- 6.9%–67.7%
| الترتيب | مقارنة | النموذج | النتيجة |
|---|---|---|---|
| 51 |  GPT-6.1 Terra (Low) OpenAI | 52.4% | |
| 52 |  Inkling 2 Small Thinking Machines | 52.3% | |
| 53 |  Qwen3.8 Max (0902) Alibaba | 52.1% | |
| 54 |  JT-4.1 Flash 236B A21B (Reasoning) China Mobile | 52.0% | |
| 55 |  Claude Haiku 5.5 (Xhigh) Anthropic | 51.7% | |
| 56 | GPT-6 Luna (Xhigh) OpenAI | 51.7% | |
| 57 |  GLM-5.3-Flash Z AI | 51.6% | |
| 58 | GPT-6.1 Terra (High) OpenAI | 51.6% | |
| 59 | GPT-6.1 Terra (Medium) OpenAI | 51.6% | |
| 60 |  MiMo-V2.6-Flash Xiaomi | 51.3% | |
| 61 |  DeepSeek V4 Pro 0813 (Max) DeepSeek | 51.0% | |
| 62 | GPT-6 Luna (Medium) OpenAI | 50.9% | |
| 63 | Qwen3.8-Flash-Next Alibaba | 50.6% | |
| 64 | GPT-6 Luna (High) OpenAI | 50.3% | |
| 65 | DeepSeek V4 Flash Vision (Max) DeepSeek | 49.7% | |
| 66 | Inkling Small Thinking Machines | 49.7% | |
| 67 | Claude Haiku 5.5 (Low) Anthropic | 49.2% | |
| 68 | 49.1% | ||
| 69 | Claude Haiku 5.5 (Medium) Anthropic | 49.0% | |
| 70 |  Agnes 2.5 Pro Beta Sapiens AI | 48.8% | |
| 71 | Claude Haiku 5.5 (High) Anthropic | 48.7% | |
| 72 |  Hy3 Tencent | 48.6% | |
| 73 |  Beam 1.0 Reflection | 48.5% | |
| 74 |  Quasar 438B (Max, Based on GLM-5.2) Multiverse Computing | 48.1% | |
| 75 |  Solar Open2 250B Upstage | 48.0% | |
| 76 | Solar Pro 4 Upstage | 48.0% | |
| 77 | 47.8% | ||
| 78 |  Kimi K2.7 Code Kimi | 47.8% | |
| 79 |  Nemotron 3.5 Super VL NVIDIA | 47.8% | |
| 80 | Solar Mini 4 Upstage | 47.6% | |
| 81 |  MiniMax-M3 MiniMax | 47.1% | |
| 82 | Inkling (Xhigh) Thinking Machines | 47.0% | |
| 83 | GPT-6 Luna (Low) OpenAI | 46.9% | |
| 84 | Qwen3.8 27B (Xhigh) Alibaba | 46.6% | |
| 85 | Qwen3.7 Plus Alibaba | 46.1% | |
| 86 |  Apodex 1.1 Apodex | 45.5% | |
| 87 |  Gemma 4 31B (Reasoning) Google | 45.5% | |
| 88 |  Ring-2.6-1T InclusionAI | 45.0% | |
| 89 | 44.9% | ||
| 90 | 44.8% | ||
| 91 | Ling-3.0-flash-VL InclusionAI | 44.2% | |
| 92 | 43.3% | ||
| 93 | 43.1% | ||
| 94 |  K2 Horizon 375B A23B Institute of Foundation Models | 42.9% | |
| 95 | Ling-3.0-flash-Fin InclusionAI | 42.4% | |
| 96 |  Motif 3 Motif Technologies | 42.2% | |
| 97 | GLM-5.3 (Low) Z AI | 42.0% | |
| 98 |  K-EXAONE 2.0 LG AI Research | 42.0% | |
| 99 | Gemini 3.5 Flash-Lite Google | 41.3% | |
| 100 |  A.X-K2 SK Telecom | 41.0% |
