Codesota · Models · Qwen2.5-VL 32BAlibaba2 results · 2 benchmarks
Model card

Qwen2.5-VL 32B.

Alibabaopen-sourceVision-Language Model

Qwen2.5 32B vision-language model.

§ 02 · Benchmarks

Every benchmark Qwen2.5-VL 32B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01ThaiOCRBenchComputer Vision · Optical Character Recognitionted-score0.8%#3/5—source ↗
02MME-VideoOCRComputer Vision · General OCR Capabilitiestotal-accuracy61.0%#6/6—source ↗
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 Qwen2.5-VL 32B actually performs.

Computer Vision
2
benchmarks
avg rank #4.5
§ 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
Qwen3.5-27B
6 results
Qwen3.5-35B-A3B
6 results
Qwen2-VL 7B
7B params · 5 results
Qwen2.5-72B-Instruct
72B params · 4 results
§ 06 · Sources & freshness

Where these numbers come from.

alphaxiv-leaderboard
2
results
0 of 2 rows marked verified.