A new benchmark, ProgramBench, has been used to evaluate Fable 5, with results suggesting it significantly outperforms Opus 4.8. The benchmark creator noted that Fable 5's performance was double that of Opus 4.8, even when Fable 5 utilized a fallback mechanism to Opus 4.8 for certain tasks. An interesting observation was that the fallback to Opus 4.8 within Fable 5 consumed twice as many tokens as Opus 4.8 would on its own for similar tasks. AI
IMPACT Fable 5's performance doubling Opus 4.8 on ProgramBench suggests a significant leap in capability, potentially pressuring competitors.
RANK_REASON The cluster reports on a benchmark result for a specific AI model, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →