‹ PublicAI Index
The LLM benchmark aggregator.
Qwen3.7 Plus
Alibaba
Strongest in Computer use (#8 of 68, on 1 of its 2 boards), weakest in Legal (#144 of 173). Above par in 4 of 10 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Muse Spark 1.1 and ahead of Qwen3.6 Plus and GLM-4.7.
§ 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.
Human preference62−6.8#59/3541/1
Human preference62−6.8#59/3541/1
Agents53.3−13.1#76/2983/6
Computer use62.3−5.8#8/681/2
Knowledge work49.2−21.5#101/2082/2
Coding45.7−20.5#119/1791/6
Agentic coding45.4−21.5#115/1731/5
Professional47.1−15.3#137/1941/2
Finance48.5−13.9#107/1621/1
Legal42.2−23.7#144/1731/1
§ 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 Qwen3.7 Plus, left for the other.
§ 3 · Sources
Where the numbers come from
5 publications, 9 figures. Every one links to the page it was read from.
LMArena Text 1455
GDPval-AA 775
AA-Briefcase 915
OSWorld 73.3%
Vals · Legal Research Bench 16.35%Vals · Finance Agent 38.22%Vals · MortgageTax 66.18%Vals · Vibe Code Bench 46.39% (OpenHands)Vals · Code Migration 12.86%
Badge
[](https://publicai.io/model-index/m/qwen3-7-plus)