Skip to content
Model Pareto

Qwen3 Omni 30B A3B Instruct

Alibaba QwenOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
$0.25/M tok
Output
$0.97/M tok
Blended
$0.43/M tok · 3:1
Speed
96tok/s
Context
66Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Qwen3 Omni 30B A3B Instruct. Price = AA median host price.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
1× H200 141GB
FP8 weights
Throughput
~8,367 tok/s
many requests batched
Price
$0.046–0.38 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, 300+ tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (35.3B params, 3B active per token) + 25% KV-cache headroom ≈ 44 GB
  • 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~8,367 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~155,846 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Writing & chat

MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. #4gpt-oss-120b81.3%
  4. ~#5Qwen3 Omni 30B A3B InstructEstimated<81.3%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#44 of 54 (estimated)~1333 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #43gpt-oss-120b1338
  4. ~#44Qwen3 Omni 30B A3B InstructEstimated1333
  5. #44INTELLECT-3Few votes1327
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#44 of 54 (estimated)~1355 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #43INTELLECT-31356
  4. ~#44Qwen3 Omni 30B A3B InstructEstimated1355
  5. #44gpt-oss-120b1352
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Qwen3 Omni 30B A3B InstructEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~last of 9 (estimated)below measured range (<74.5%)
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #8Gemini 3.5 Flash-Lite74.5%
  4. ~#9Qwen3 Omni 30B A3B InstructEstimated<74.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~last of 8 (estimated)below measured range (<75.8%)
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #7Muse Glimmer75.8%
  4. ~#8Qwen3 Omni 30B A3B InstructEstimated<75.8%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#36 of 43 (estimated)~1.9%
  1. #1GPT-6 Astra31.0%
  2. #2Muse Spark 1.326.6%
  3. #35Mistral Medium 3.52.8%
  4. ~#36Qwen3 Omni 30B A3B InstructEstimated1.9%
  5. #36Ministral 3 14B1.2%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 23 (estimated)below measured range (<9.0%)
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #22Mistral Large 39.0%
  4. ~#23Qwen3 Omni 30B A3B InstructEstimated<9.0%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#14 of 25 (estimated)~48.5%
  1. #1Inkling97.1%
  2. #2Muse Glimmer94.7%
  3. #13Phi-4-reasoning-plus78.0%
  4. ~#14Qwen3 Omni 30B A3B InstructEstimated48.5%
  5. #14Mistral Large 338.0%
No published score — estimated from related benchmarks

Agents

OSWorld-VerifiedEstimated
~#11 of 12 (estimated)~65.4%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Muse Glimmer65.9%
  4. ~#11Qwen3 Omni 30B A3B InstructEstimated65.4%
  5. #11Claude Haiku 4.550.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Qwen3 Omni 30B A3B InstructEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#56 of 87 (estimated)~682 Elo
  1. #1Claude Opus 5.51846
  2. #2Claude Fable 5.11735
  3. #55MiniCPM5-2B694
  4. ~#56Qwen3 Omni 30B A3B InstructEstimated682
  5. #56Nemotron 3.5 Lightning624
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#70 of 89 (estimated)~6.7%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #68Qwen3.5 9B7.0%
  4. ~#70Qwen3 Omni 30B A3B InstructEstimated6.7%
  5. #70Ministral 3 14B6.6%
No published score — estimated from related benchmarks