‹ PublicAI Index
The LLM benchmark aggregator.
Qwen3 Coder Next
Alibaba · 80B · open weights
Strongest in Knowledge work (#120 of 177), weakest in Agents (#195 of 267). Above par in 0 of 4 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and GPT-6 Astra and ahead of Command A and UI-TARS 1.5 7B.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Core abilities42.9−24.5#171/2041/3
General intelligence39.8−30.3#177/2041/3
Agents44.2−23.9#195/2672/5
Knowledge work42.4−31.2#120/1772/2
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Qwen3 Coder Next, left for the other.
§ 3 · Sources
Where the numbers come from
3 publications, 3 figures. Every one links to the page it was read from.
Artificial Analysis Intelligence Index 9
GDPval-AA 501
AA-Briefcase 405
Badge
[](https://publicai.io/model-index/m/qwen3-coder-next)