| الترتيب | مقارنة | النموذج | النتيجة | التكلفة / المهمة | الوقت / المهمة | tokens المخرجات / المهمة |
|---|---|---|---|---|---|---|
| 51 | 20.2% | — | — | — | ||
| 52 |  Grok 4.7 (Xhigh) SpaceXAI | 20.0% | $0.32 | 4m 27s | 17K | |
| 53 |  MiMo-V2.6-Pro Xiaomi | 19.2% | $0.024 | 2m 44s | 9.26K | |
| 54 |  Gemini 3.8 Flash (Low) Google | 18.6% | — | — | — | |
| 55 |  GPT-6 Luna (Xhigh) OpenAI | 18.6% | $0.021 | 1m 28s | 9.06K | |
| 56 | 18.6% | $0.19 | 42.5s | 7.34K | ||
| 57 |  Claude Haiku 5.5 (Xhigh) Anthropic | 18.2% | $0.027 | 1m 22s | 19.4K | |
| 58 | GPT-6 Luna (High) OpenAI | 18.2% | $0.019 | 55.5s | 5.38K | |
| 59 | Gemini 3.1 Pro Preview Google | 17.8% | — | — | — | |
| 60 |  Mistral Large 4 (High) Mistral | 17.6% | $0.11 | 1m 6s | 7.68K | |
| 61 | Claude Haiku 5.5 (High) Anthropic | 17.2% | $0.023 | 43.7s | 9.98K | |
| 62 |  DeepSeek V4.1 Flash 1017 (Max) DeepSeek | 17.2% | $0.042 | 1m 59s | 16.4K | |
| 63 | Mistral Large 4 (Medium) Mistral | 16.8% | $0.099 | 43.6s | 4.91K | |
| 64 |  Qwen3.8 27B (Xhigh) Alibaba | 16.4% | $0.096 | 4m 3s | 11.2K | |
| 65 | 16.0% | $0.37 | 13.8s | 1.93K | ||
| 66 | Qwen3.8 2.4T A95B Alibaba | 15.6% | — | — | — | |
| 67 | Qwen3.8-Flash-Next Alibaba | 15.6% | — | — | — | |
| 68 |  GLM-5.3-Flash Z AI | 15.4% | $0.032 | 5m 17s | 15.7K | |
| 69 | Claude Haiku 5.5 (Medium) Anthropic | 15.2% | $0.021 | 26.6s | 5.99K | |
| 70 |  Step 5 Preview StepFun | 14.8% | $0.12 | 1m 32s | 13.2K | |
| 71 |  Agnes 2.5 Pro Theta Sapiens AI | 14.2% | $0.014 | 1m 11s | 13.8K | |
| 72 | DeepSeek V4.1 Flash 1017 (High) DeepSeek | 14.2% | $0.034 | 1m 4s | 9.01K | |
| 73 | GPT-6 Luna (Medium) OpenAI | 13.8% | $0.017 | 26.1s | 2.59K | |
| 74 | Gemini 3.5 Flash-Lite Google | 13.6% | $0.039 | 17.2s | 5.35K | |
| 75 |  Inkling (Xhigh) Thinking Machines | 12.8% | $0.14 | 2m 4s | 12K | |
| 76 | Qwen3.8 27B (Medium) Alibaba | 12.8% | $0.071 | 1m 32s | 4.12K | |
| 77 |  Ling 3.1 Flash 1019 InclusionAI | 12.6% | $0.034 | — | 25.4K | |
| 78 | 12.6% | — | — | — | ||
| 79 | 12.2% | — | — | — | ||
| 80 | Qwen3.7 Plus Alibaba | 12.2% | — | — | — | |
| 81 | DeepSeek V4 Flash Vision (Max) DeepSeek | 12.0% | — | — | — | |
| 82 |  Beam 1.0 Reflection | 11.6% | $0.028 | 38.5s | 11.1K | |
| 83 | DeepSeek V4 Pro 0813 (Max) DeepSeek | 11.4% | $0.11 | 4m 0s | 16.6K | |
| 84 |  Apodex 1.1 Apodex | 11.2% | $0.054 | 1m 28s | 12.4K | |
| 85 | Claude Haiku 5.5 (Low) Anthropic | 11.2% | $0.019 | 15.6s | 3.4K | |
| 86 | GLM-5.3 (Max) Z AI | 11.2% | $0.17 | 6m 54s | 28.4K | |
| 87 |  Hy3 Tencent | 11.2% | — | — | — | |
| 88 | Inkling Small Thinking Machines | 11.2% | $0.037 | 2m 24s | 10.3K | |
| 89 |  Kimi K2.7 Code Kimi | 11.2% | — | — | — | |
| 90 |  Nanbeige4.3-33B Nanbeige | 11.2% | — | — | 25.5K | |
| 91 | Qwen3.8 27B (Low) Alibaba | 10.4% | $0.07 | 1m 6s | 3.32K | |
| 92 | Ling 3.1 Flash InclusionAI | 10.0% | — | — | — | |
| 93 | 10.0% | $0.023 | 55.0s | 4.92K | ||
| 94 |  MiniMax-M3 MiniMax | 9.8% | $0.053 | 1m 4s | 7.94K | |
| 95 | GPT-6 Luna (Low) OpenAI | 9.0% | $0.017 | 10.8s | 935 | |
| 96 | MiMo-V2.6-Flash Xiaomi | 9.0% | $0.02 | 2m 37s | 5.51K | |
| 97 | GLM-5.3 (Low) Z AI | 8.8% | $0.063 | 57.1s | 3.37K | |
| 98 |  JT-4.1 Flash 236B A21B (Reasoning) China Mobile | 8.6% | — | — | — | |
| 99 | Ling-3.0-flash-VL InclusionAI | 8.4% | — | — | — | |
| 100 |  Nemotron 3.5 Super VL NVIDIA | 8.0% | $0.018 | 27.8s | 7.22K |
