Codesota · Models · Qwen3.5-27BAlibaba16 results · 10 benchmarks
Model card

Qwen3.5-27B.

Alibabaopen-source
§ 02 · Benchmarks

Every benchmark Qwen3.5-27B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01MMMUMultimodal · Image-Text-to-Textaccuracy82.3%#4/36source ↗
02MMStarMultimodal · Image-Text-to-Textaccuracy81.0%#5/21source ↗
03RealWorldQAMultimodal · Visual Question Answeringaccuracy83.7%#7/23source ↗
04Tau2-BenchAgentic AI · Tool Useaccuracy79.0%#8/11source ↗
05BrowseCompNatural Language Processing · Question Answeringaccuracy61.0%#9/16source ↗
06MVBenchMultimodal · Video Understandingaccuracy74.6%#9/20source ↗
07MMMU-ProMultimodal · Visual Question Answeringaccuracy75.0%#13/31source ↗
08SWE-Bench VerifiedComputer Code · Code Generationaccuracy72.4%#13/22source ↗
09GPQA DiamondReasoning · Multi-step Reasoningaccuracy85.5%#20/74source ↗
10PLCCNatural Language Processing · Polish Cultural Competencygrammar62.0%#77/165source ↗
11PLCCNatural Language Processing · Polish Cultural Competencyvocabulary54.0%#84/165source ↗
12PLCCNatural Language Processing · Polish Cultural Competencygeography64.0%#105/165source ↗
13PLCCNatural Language Processing · Polish Cultural Competencyaverage54.3%#105/165source ↗
14PLCCNatural Language Processing · Polish Cultural Competencyhistory63.0%#115/165source ↗
15PLCCNatural Language Processing · Polish Cultural Competencyculture-and-tradition46.0%#115/165source ↗
16PLCCNatural Language Processing · Polish Cultural Competencyart-and-entertainment37.0%#124/165source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where Qwen3.5-27B actually performs.

Multimodal
5
benchmarks
avg rank #7.6
Agentic AI
1
benchmark
avg rank #8.0
Computer Code
1
benchmark
avg rank #13.0
Reasoning
1
benchmark
avg rank #20.0
Natural Language Processing
2
benchmarks
avg rank #91.8
§ 04 · Papers

1 paper with results for Qwen3.5-27B.

  1. 2026-02-16· 9 results

    Qwen3.5: Towards Native Multimodal Agents

§ 05 · Related models

Other Alibaba models scored on Codesota.

Qwen3-235B-A22B
235B (22B active) params · 9 results · 1 SOTA
Qwen2-VL 72B
9 results
Qwen3.5-397B-A17B
8 results
Qwen3.5-122B-A10B
6 results
Qwen3.5-35B-A3B
6 results
Qwen2-VL 7B
7B params · 5 results
Qwen2.5-72B-Instruct
72B params · 4 results
Qwen2.5-Coder 32B
32B params · 4 results
§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
9
results
sdadas/PLCC
7
results
7 of 16 rows marked verified.