Fetching from the wire…
01
02
03
04
05
06
07
08
Models2026-08-08 · source-backed
Alibaba's model was reported best overall on Artificial Analysis' Agentic Index, drawing 540 points on HN. Readers watching the page saw Qwen at 55.4 vs Opus Max at 55.3, then on reload Opus Max at 59.2 vs Qwen at 58.4. George from Artificial Analysis replied in-thread that they'd shipped a planned upgrade to equality-checking/grader models plus the latest τ³-Banking version that day. Opus 5 remains first on the broader Intelligence Index. The lesson isn't about either model, it's that grader changes move a public leaderboard a full point within hours and single-snapshot rankings aren't durable evidence of anything.
Each link below shares sources, entities, or timing with this story.
Alibaba released Qwen / Shared entities / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Alibaba released Qwen); both cover Alibaba, Opus, Qwen, Qwen3; overlapping topics (agentic, model).
Ollama supports Qwen / Shared entities / Earlier coverage / Tension
Linked by a graph relationship (Ollama supports Qwen); both cover Alibaba, Opus, Qwen, Qwen3; earlier Alibaba coverage from 2026-04-23.
Alibaba released Qwen / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Alibaba released Qwen); both cover Alibaba, Qwen; reported by the same outlet (news.ycombinator.com).
Anthropic criticizes Qwen / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Anthropic criticizes Qwen); both cover Artificial Analysis, Intelligence Index, Opus; overlapping topics (analysi, artificial).
Alibaba released Qwen / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Alibaba released Qwen); both cover Alibaba, Qwen, Qwen3; overlapping topics (alibaba, qwen).
Alibaba released Qwen / Shared entities / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Alibaba released Qwen); both cover Alibaba, Opus; overlapping topics (model, opus).
Anthropic criticizes Qwen / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Anthropic criticizes Qwen); both cover Alibaba, Qwen; overlapping topics (agentic, alibaba, model).
Qwen benchmarked against Claude / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Qwen benchmarked against Claude); both cover Opus, Qwen3; overlapping topics (agentic, model, opus).