iFANN
    ابحث في iFANN...
    تسجيل الدخول
    الرئيسية
    الأخبار
    فيديوهات
    صور
    صور GIF
    استكشاف
    استطلاعات
    الجوائز
    iFAMOUS
    ويكي
    أنمي
    غرف
    الإشعارات
    الرسائل
    المحفوظات
    الملف الشخصي
    ويكيالجوائزiFAMOUSالتصنيفاتالقطاعاتمكافآت المبدعينمكافآت المستخدمينالشروطالخصوصيةإرشادات المجتمعالإزالة / DMCAالمساعدةالمطورون

    © 2026 iFANN

    الرئيسية
    بحث
    الرسائل
    التنبيهات
    الملف الشخصي
    صورة
    Estebankiwi
    Estebankiwi@estebankiwi5mo
    💭AI📱GPT🎮Claude
    AI coding benchmark comparison

    @estebankiwiLocal AI models are now surpassing GPT-5 on coding benchmarks. Consider this: Gemma 4 31B achieves a score of 38.7, Qwen 3.6 27B scores 36.5, and GPT-5 trails at 36.0. These are models you can run on a MacBook, outperforming what was considered the smartest model in the world just nine months ago. GPT-5.5 currently leads at 59.1, with Claude Opus 4.7 at 52.5. The gap between frontier models and local ones is still significant, but it is closing every day. It seems inevitable that we will soon have models rivaling GPT-5.5 and Claude Opus 4.7 running on consumer hardware. The trajectory is unmistakable.

    عرض المنشور الأصلي

    AI coding benchmark comparison

    صورة بواسطة @estebankiwi· May 27, 2026· AI

    عن هذه الصورة

    The image shows a screenshot of a bar graph comparing the Artificial Analysis Coding Index of seven AI models. The graph displays the models' performance with colored bars, each labeled with the model's name and score. The mood/style is technical and informative, suggesting a professional or analytical context. Notable details include the highlighted bars for Gemini 4 3IB and GPT-5, surrounded by blue and red boxes respectively, and the presence of various logos and icons representing the AI models.

    عرض كل صور AI

    ?

    المزيد من صور AI

    عرض كل صور AI
    OWC external hard drive with SD card slotOWC external hard drive with SD card slotJoanna Maciejewska opinion on AI choresJoanna Maciejewska opinion on AI choresMelvin Dvivas grokbot Kanban boardMelvin Dvivas grokbot Kanban boardNVIDIA engineer resignationNVIDIA engineer resignationtoo realtoo realOpenAI AI robots for data centers and chips2OpenAI AI robots for data centers and chipsFastMCP GitHub Repository v4.2FastMCP GitHub Repository v4.2OpenAI launches ChatGPT WalletOpenAI launches ChatGPT WalletFAA SMART AI tool and the ground stopFAA SMART AI tool and the ground stopClaude Duet US rolloutClaude Duet US rollout
    صورة
    Estebankiwi
    Estebankiwi@estebankiwi5mo
    💭AI📱GPT🎮Claude
    AI coding benchmark comparison

    @estebankiwiLocal AI models are now surpassing GPT-5 on coding benchmarks. Consider this: Gemma 4 31B achieves a score of 38.7, Qwen 3.6 27B scores 36.5, and GPT-5 trails at 36.0. These are models you can run on a MacBook, outperforming what was considered the smartest model in the world just nine months ago. GPT-5.5 currently leads at 59.1, with Claude Opus 4.7 at 52.5. The gap between frontier models and local ones is still significant, but it is closing every day. It seems inevitable that we will soon have models rivaling GPT-5.5 and Claude Opus 4.7 running on consumer hardware. The trajectory is unmistakable.

    عرض المنشور الأصلي

    AI coding benchmark comparison

    صورة بواسطة @estebankiwi· May 27, 2026· AI

    عن هذه الصورة

    The image shows a screenshot of a bar graph comparing the Artificial Analysis Coding Index of seven AI models. The graph displays the models' performance with colored bars, each labeled with the model's name and score. The mood/style is technical and informative, suggesting a professional or analytical context. Notable details include the highlighted bars for Gemini 4 3IB and GPT-5, surrounded by blue and red boxes respectively, and the presence of various logos and icons representing the AI models.

    عرض كل صور AI

    ?

    المزيد من صور AI

    عرض كل صور AI
    OWC external hard drive with SD card slotOWC external hard drive with SD card slotJoanna Maciejewska opinion on AI choresJoanna Maciejewska opinion on AI choresMelvin Dvivas grokbot Kanban boardMelvin Dvivas grokbot Kanban boardNVIDIA engineer resignationNVIDIA engineer resignationtoo realtoo realOpenAI AI robots for data centers and chips2OpenAI AI robots for data centers and chipsFastMCP GitHub Repository v4.2FastMCP GitHub Repository v4.2OpenAI launches ChatGPT WalletOpenAI launches ChatGPT WalletFAA SMART AI tool and the ground stopFAA SMART AI tool and the ground stopClaude Duet US rolloutClaude Duet US rollout