Benchmark Almanac

Qwen3-VL-32B-Instruct

Qwen3-VL-32B-Instruct ranks first on HR-Bench.

Qwen Released October 21st, 2025 Family Qwen3-VL The lab's model card Compare with others
9
Benchmarks with a score
1
Ranked first, out of five or more models
3
In the top three
Qwen Oct 2025

Qwen3-VL-32B-Instruct

Open weights Small

No Epoch Capabilities Index score yet
  • HR-Bench 83% #1 /8
  • RefAdv-S 59% #9 /19
  • LMBuild 31% #14 /18

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
SEA-HELM 67.0 #37 of 71 Official leaderboard

Professional work

BenchmarkScoreRankSource
LMBuild 31% #14 of 18 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
HR-Bench 83% #1 of 8 Official leaderboard
LEGO-Puzzles 57% #3 of 16 Official leaderboard
MMOU 44% #2 of 5 Official leaderboard
RefAdv-S 59% #9 of 19 Official leaderboard
WorldVQA 17.7% #13 of 22 Official leaderboard
DISBench 8.20% #8 of 9 Official leaderboard

Safety and security

BenchmarkScoreRankSource
nocot-bench (NCRI) 64.0 #124 of 185 Official leaderboard