Skip to content
Model Pareto

Qwen3.5 397B A17B

Alibaba QwenOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
$0.60/M tok
Output
$3.60/M tok
Blended
$1.35/M tok · 3:1
Speed
86tok/s
Context
262Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Qwen3.5 397B A17B (Reasoning). 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
4× B200 180GB
FP8 weights
Throughput
~12,969 tok/s
many requests batched
Price
$0.20–1.76 /M tok
busy → light use
On your own machine
Mac Studio M5 Ultra 512GB (int4, ~99 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (397B params, 17B active per token) + 25% KV-cache headroom ≈ 496 GB
  • 4× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~12,969 output tok/s aggregate at batch 371 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~250,147 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.

Coding

SWE-bench VerifiedEstimated
~#9 of 14 (estimated)~75.1%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. #8Muse Glimmer76.0%
  4. ~#9Qwen3.5 397B A17BEstimated75.1%
  5. #9Xing4.0-29B-A4B75.0%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#15 of 19 (estimated)~54.3%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #14Inkling54.3%
  4. ~#15Qwen3.5 397B A17BEstimated54.3%
  5. #15Gemini 3.1 Pro54.2%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#27 of 31 (estimated)~51.8%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #26Nex-N2.5-Pro55.8%
  4. ~#27Qwen3.5 397B A17BEstimated51.8%
  5. #27Qwen3.8 Max (0902)51.0%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#8 of 20 (estimated)~73.5%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #7gpt-oss-20b77.7%
  4. ~#8Qwen3.5 397B A17BEstimated73.5%
  5. #8Mistral Small 464.0%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~last of 15 (estimated)below measured range (<41.1)
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #14GPT-6 Luna41.1
  4. ~#15Qwen3.5 397B A17BEstimated<41.1
No published score — estimated from related benchmarks

Writing & chat

MMMLUEstimated
~#3 of 5 (estimated)~87.7%
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. ~#3Qwen3.5 397B A17BEstimated87.7%
  4. #3Claude Haiku 4.583.0%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#27 of 531434 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #26Grok 4.71435
  4. #27Qwen3.5 397B A17B1434
  5. #28Inkling1430
lmarena.ai · 2026-09-13
LMArena Text (Elo)Verified
#25 of 531442 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #25GPT-6 Luna1442
  4. #25Qwen3.5 397B A17B1442
  5. #27MiniMax-M31441
lmarena.ai · 2026-09-13

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Qwen3.5 397B A17BEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#6 of 9 (estimated)~78.6%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #5Muse Glimmer78.8%
  4. ~#6Qwen3.5 397B A17BEstimated78.6%
  5. #6Inkling78.1%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#5 of 8 (estimated)~84.7%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #4Gemini 3.1 Pro85.3%
  4. ~#5Qwen3.5 397B A17BEstimated84.7%
  5. #5Claude Haiku 4.579.6%
No published score — estimated from related benchmarks
ChartographyEstimated
~#15 of 23 (estimated)~18.5%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #14Grok 4.620.5%
  4. ~#15Qwen3.5 397B A17BEstimated18.5%
  5. #15Muse Glimmer17.2%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#5 of 25 (estimated)~93.2%
  1. #1Inkling97.1%
  2. #2Muse Glimmer94.7%
  3. #4gpt-oss-120b93.4%
  4. ~#5Qwen3.5 397B A17BEstimated93.2%
  5. #5Xing4.0-29B-A4B90.0%
No published score — estimated from related benchmarks

Agents

OSWorld-VerifiedEstimated
~#11 of 12 (estimated)~65.7%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Muse Glimmer65.9%
  4. ~#11Qwen3.5 397B A17BEstimated65.7%
  5. #11Claude Haiku 4.550.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #4GPT-5.547.5%
  4. ~#5Qwen3.5 397B A17BEstimated<47.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#15 of 18 (estimated)~63.3%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #14Inkling77.1%
  4. ~#15Qwen3.5 397B A17BEstimated63.3%
  5. #15Mistral Medium 3.548.6%
No published score — estimated from related benchmarks