‹ PublicAI Index
The LLM benchmark aggregator.
Qwen 3.5 Plus
Alibaba
Strongest in Medical (#31 of 149), weakest in Safety (#197 of 329). Above par in 9 of 13 scopes. Among the models it meets almost everywhere, it finishes behind GPT-5.5 and Claude Opus 5 and ahead of DeepSeek V4 Pro and Kimi K2.6.
§ 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.
Reasoning55.2−10.2#42/1951/5
Science57.9−5.6#38/1221/1
Mathematics55.3−8.5#50/1521/2
Professional53.9−8.5#44/1941/2
Medical56.2−10.3#31/1491/1
Legal54−11.9#55/1731/1
Finance53.7−8.7#70/1621/1
Knowledge53.1−9.4#61/1971/3
Academic knowledge57.4−6.5#33/1231/1
Coding45.1−21.1#128/1791/6
Agentic coding44.7−22.2#123/1731/5
Safety49.4−12#197/3291/3
Factual grounding48.1−22.6#67/1041/1
§ 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 Qwen 3.5 Plus, left for the other.
§ 3 · Sources
Where the numbers come from
2 publications, 11 figures. Every one links to the page it was read from.
Vals · CaseLaw 59.7%Vals · LegalBench 85.1%Vals · CorpFin 65.31%Vals · MortgageTax 60.77%Vals · MedQA 95.21%Vals · SWE-bench Verified 71.2% (Mini-SWE-agent)Vals · Vibe Code Bench 15.74% (OpenHands)Vals · GPQA Diamond 87.37%Vals · MMLU Pro 87.18%Vals · AIME 86.04%
Vectara · Factual consistency 89.3%
Badge
[](https://publicai.io/model-index/m/qwen-3-5-plus)