Hacker News

Qwen3.8 Max now ranked as the best overall model by agentic index

Alibaba's Qwen3.8-Max takes on GPT-5.6 Sol and Claude Fable 5 with ...

Artificial AnalysisKIndependent analysis of AIUnderstand the AI landscape to choose the best model and provider for your use caseUpdateIntelligence Index v4.1.1Intelligence Index v4.1.1 moves ๐œยณ-Banking to v1.0.1 and upgrades the grader for HLE, AA-LCR, and AA-Omniscience to GPT-5.6 Luna (medium)LaunchEndpoint Accuracy IndexMeasuring whether provider endpoints serve the same model quality as the referenceHighlightsIntelligenceArtificial Analysis Intelligence Index ยท Higher is betterSpeedOutput tokens per second ยท Higher is betterCost per TaskWeighted average cost (USD) per Intelligence Index task ยท Lower is betterPersonalized model recommenderGet personalized recommendations based on your priorities for intelligence, speed, and costExplore agents for general work, coding, customer…

Continue reading at Hacker News artificialanalysis.ai
Advertisement