iFANN
    Cerca su iFANN...
    Accedi
    Home
    Notizie
    Video
    Foto
    GIF
    Esplora
    Sondaggi
    Premi
    iFAMOUS
    Wiki
    Anime
    Stanze
    Notifiche
    Messaggi
    Segnalibri
    Profilo
    WikiPremiiFAMOUSClassificheSettoriRicompense CreatorRicompense UtenteTerminiPrivacyLinee guida della communityRimozione / DMCAAiutoSviluppatori

    © 2026 iFANN

    Home
    Cerca
    Messaggi
    Avvisi
    Profilo
    Foto
    Estebankiwi
    Estebankiwi@estebankiwi3mo
    đŸ“±GPT💭AI💭Tech
    Claude Fable 5 DeepSWE benchmark

    @estebankiwiClaude Fable 5 has claimed the top spot on DeepSWE with a score of 70%. However, the performance gap between Fable 5 and GPT 5.5 is far more significant than just three percentage points. Fable 5 generates code that reads as if it were written by a senior engineer, while GPT 5.5 produces code that simply passes the tests. Both models deliver functional software, but only one delivers software that truly impresses.

    Vedi post originale

    Claude Fable 5 DeepSWE benchmark

    Foto di @estebankiwi· Jun 19, 2026· GPT

    Su questa foto

    The image shows a horizontal bar chart comparing AI models. The focus is on a table with model names, performance metrics, and bars representing their performance. The model "claude-fable-5" is highlighted with a red rectangle around it and its corresponding bar is orange. The table columns are labeled "MODEL", "PASS@1", "AVG COST", "OUT TOK", and "STEPS". The model names listed are claude-fable-5, gpt-5.5, claude-opus-4.8, gpt-5.4, gemini-3.5-flash, and kimi-k2.7-code. No on-screen text stands out aside from the column headers and model names.

    Vedi tutte le foto di GPTLeggi la wiki di GPT

    ?

    Altre foto di GPT

    Vedi tutte le foto di GPT
    AI as your doctor?AI as your doctor?GPT 6 Astra effort comparison tableGPT 6 Astra effort comparison tablemanual coding psychopathmanual coding psychopathJensen Huang AGI has arrived GPT-6 Astra2Jensen Huang AGI has arrived GPT-6 AstraAI Breakfast greatest predictionAI Breakfast greatest predictionweekend plans cancelledweekend plans cancelledAI Image Models ComparisonAI Image Models Comparison
    Foto
    Estebankiwi
    Estebankiwi@estebankiwi3mo
    đŸ“±GPT💭AI💭Tech
    Claude Fable 5 DeepSWE benchmark

    @estebankiwiClaude Fable 5 has claimed the top spot on DeepSWE with a score of 70%. However, the performance gap between Fable 5 and GPT 5.5 is far more significant than just three percentage points. Fable 5 generates code that reads as if it were written by a senior engineer, while GPT 5.5 produces code that simply passes the tests. Both models deliver functional software, but only one delivers software that truly impresses.

    Vedi post originale

    Claude Fable 5 DeepSWE benchmark

    Foto di @estebankiwi· Jun 19, 2026· GPT

    Su questa foto

    The image shows a horizontal bar chart comparing AI models. The focus is on a table with model names, performance metrics, and bars representing their performance. The model "claude-fable-5" is highlighted with a red rectangle around it and its corresponding bar is orange. The table columns are labeled "MODEL", "PASS@1", "AVG COST", "OUT TOK", and "STEPS". The model names listed are claude-fable-5, gpt-5.5, claude-opus-4.8, gpt-5.4, gemini-3.5-flash, and kimi-k2.7-code. No on-screen text stands out aside from the column headers and model names.

    Vedi tutte le foto di GPTLeggi la wiki di GPT

    ?

    Altre foto di GPT

    Vedi tutte le foto di GPT
    AI as your doctor?AI as your doctor?GPT 6 Astra effort comparison tableGPT 6 Astra effort comparison tablemanual coding psychopathmanual coding psychopathJensen Huang AGI has arrived GPT-6 Astra2Jensen Huang AGI has arrived GPT-6 AstraAI Breakfast greatest predictionAI Breakfast greatest predictionweekend plans cancelledweekend plans cancelledAI Image Models ComparisonAI Image Models Comparison