Benchmark Almanac

Qwen3-VL-30B-A3B-Instruct

Qwen3-VL-30B-A3B-Instruct places in the top three on HR-Bench.

Qwen Released October 4th, 2025 Family Qwen3-VL The lab's model card Compare with others
10
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Qwen Oct 2025

Qwen3-VL-30B-A3B-Instruct

Open weights Small

No Epoch Capabilities Index score yet
  • HR-Bench 80.9% #2 /8
  • ChartMuseum 40.2% #16 /21
  • RefAdv-S 52.1% #13 /19

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
QIMMA 45.6% #18 of 25 Official leaderboard

Professional work

BenchmarkScoreRankSource
LMBuild 31.9% #13 of 18 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
HR-Bench 80.9% #2 of 8 Official leaderboard
RoboRewardBench 0.90 #9 of 22 Official leaderboard
GSM8K-V 27.9% #10 of 24 Official leaderboard
WorldVQA 18.9% #12 of 22 Official leaderboard
Daily-Omni 57.3% #9 of 14 Official leaderboard
RefAdv-S 52.1% #13 of 19 Official leaderboard
ChartMuseum 40.2% #16 of 21 Official leaderboard

Safety and security

BenchmarkScoreRankSource
nocot-bench (NCRI) 59.9 #139 of 185 Official leaderboard