Skip to content
Model Pareto

Qwen3.5 9B

Alibaba QwenOpen weightsartificialanalysis.ai ↗
Input
$0.17/M tok
Output
$0.25/M tok
Blended
$0.19/M tok · 3:1
Speed
96tok/s
Context
262Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Qwen3.5 9B (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
1× B200 180GB
BF16 weights
Throughput
~10,073 tok/s
many requests batched
Price
$0.083–0.74 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, ~280 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • BF16 weights (9B params) + 25% KV-cache headroom ≈ 23 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~10,073 output tok/s aggregate at batch 256 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~59,063 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

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Qwen3.5 9BEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
~#11 of 12 (estimated)~75.2%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #10Claude Sonnet 577.0%
  4. ~#11Qwen3.5 9BEstimated75.2%
  5. #11Gemini 3.5 Flash-Lite74.5%
No published score — estimated from related benchmarks
~#5 of 8 (estimated)~81.2%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #4Gemini 3.1 Pro85.3%
  4. ~#5Qwen3.5 9BEstimated81.2%
  5. #5Claude Haiku 4.579.6%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#35 of 48 (estimated)~9.4%
  1. #1Muse Wonder Full32.6%
  2. #2GPT-6 Astra31.0%
  3. #34MiniMax-M39.8%
  4. ~#35Qwen3.5 9BEstimated9.4%
  5. #35Ling-3.0-flash-VL8.4%
No published score — estimated from related benchmarks
ChartographyEstimated
~#22 of 25 (estimated)~10.8%
  1. #1Claude Fable 5.273.4%
  2. #2GPT-6 Astra71.0%
  3. #21DeepSeek V4.1 Flash11.6%
  4. ~#22Qwen3.5 9BEstimated10.8%
  5. #22Gemini 3.5 Flash-Lite10.2%
No published score — estimated from related benchmarks

Hard reasoning

Agents