Ctrl K
Back to models

Alibaba

Qwen3 Omni 30B A3B Instruct

  • Released
  • Open weights
  • Apache 2.0
Compare
Intelligence Index

Standard setting

6.0
Estimated · Artificial Analysis v4.3.2
Context window
65.54K tok

Performance profile

ReasoningRank #84 of 107
62.0%
GPQA Diamond

Capabilities

Context window

Modalities

Measured setting

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
StandardEstimated
Intelligence Index
6.0

Pricing & access

No API offering listed in our tracked sources.

Run locally

Original download
70.5 GB
App memory
Unverified
Documented software
TransformersSetup guide (opens in a new tab)
Find GGUF downloads (opens in a new tab)Original weights (opens in a new tab)

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

Qwen3 Omni 30B A3B Instruct · Standard#114 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 111Llama 4 MaverickStandard4.9%
  6. 112NVIDIA Nemotron Nano 9B V2Reasoning4.9%
  7. 113Nemotron 3 Nano Omni 30B A3B ReasoningReasoning4.8%
  8. 114Qwen3 Omni 30B A3B InstructStandard4.6%
  9. 114Nova MicroStandard4.6%
  10. 114Ministral 3 14BStandard4.6%
  11. 117G9v3-3BReasoning4.5%

Peers use their best measured result on this benchmark.