Benchmark Almanac

Qwen3-Omni-30B-A3B-Thinking

Qwen3-Omni-30B-A3B-Thinking ranks first on LongShOTBench.

Qwen Released September 15th, 2025 Family Qwen3-Omni The lab's model card Compare with others
6
Benchmarks with a score
1
Ranked first, out of five or more models
1
In the top three
Qwen Sep 2025

Qwen3-Omni-30B-A3B-Thinking

Open weights Mid-size

No Epoch Capabilities Index score yet
  • OmniGAIA 13.3% #5 /6
  • LongShOTBench 64.2% #1 /67
  • EvaOmni 24.8% #20 /22

Where has it been number one?

Qwen3-Omni-30B-A3B-Thinking led 1 benchmark at some point, for a median of 355 days. It still tops 1 that nobody has tested since.

Source: Official leaderboards

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.

Agents and tools

BenchmarkScoreRankSource
OmniGAIA 13.3% #5 of 6 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
LongShOTBench 64.2% #1 of 67 Official leaderboard
MMAR 66.4% #1 of 3 Official leaderboard
MusICA-MetaBench 46.3% #2 of 4 Official leaderboard
PianoBench 48.4% #14 of 16 Official leaderboard
EvaOmni 24.8% #20 of 22 Official leaderboard

Who measured it?

Independent runs cover all 6 of its benchmarks.

  • An independent run only 6
Official leaderboards scored it on 6.

Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards