bibibi.ccLoading…
Connect scattered updates into a story you can understand.
GitHub introduced the multi-model orchestration system Copilot Fusion at the Universe 2026 conference. Artificial Analysis testing shows that its coding score is close to Claude Code, with average API lower costs. 51%。
Artificial Analysis updates the Intelligence Index, adding programming and research tasks and increasing the weighting of hidden tests. Claude Opus 5.5 leads by 58 points, while DeepSeek V4.1 Flash and GLM-5.3 each score 32 points.
Artificial Analysis reports that Claude Opus 5.5 max ranked first with 58 points; GPT-6 Sol and Luna performed similarly to the previous generation, but their per-task costs fell significantly.