Qwen3.5 9B
- 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
Writing & chat
Verified#71 / 162rank by quality50.2±9.5quality / 1001/5 benchmarks measuredVision
Verified#62 / 98rank by quality46.6±8.2quality / 1001/6 benchmarks measuredHard reasoning
Verified#119 / 218rank by quality39.0±3.7quality / 1003/4 benchmarks measuredAgents
Verified#91 / 187rank by quality33.3±5.9quality / 1003/7 benchmarks measured
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
IFBenchVerified
#44 of 13966.7%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #44KAT Coder Pro V266.7%
- #44Qwen3.5 9B66.7%
- #46HyperNova 60B 260566.5%
artificialanalysis.ai · 2026-09-24
LMArena Text, Non-English (Elo)Estimated
~#42 of 57 (estimated)~1388 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #41Claude Haiku 4.51395
- ~#42Qwen3.5 9BEstimated1388
- #42GPT-5.4 nano1387
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#42 of 57 (estimated)~1405 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #41Mistral Large 31413
- ~#42Qwen3.5 9BEstimated1405
- #42GPT-5.4 nano1402
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#19 of 26 (estimated)~1561 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #18Inkling1611
- ~#19Qwen3.5 9BEstimated1561
- #19Gemini 3.5 Flash-Lite1559
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#48 of 8769.2%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #48Gemma 4 26B A4B69.2%
- #48Qwen3.5 9B69.2%
- #50Ternary Bonsai 27B69.0%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~#11 of 12 (estimated)~75.2%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #10Claude Sonnet 577.0%
- ~#11Qwen3.5 9BEstimated75.2%
- #11Gemini 3.5 Flash-Lite74.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#5 of 8 (estimated)~81.2%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #4Gemini 3.1 Pro85.3%
- ~#5Qwen3.5 9BEstimated81.2%
- #5Claude Haiku 4.579.6%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#35 of 48 (estimated)~9.4%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #34MiniMax-M39.8%
- ~#35Qwen3.5 9BEstimated9.4%
- #35Ling-3.0-flash-VL8.4%
No published score — estimated from related benchmarks
ChartographyEstimated
~#22 of 25 (estimated)~10.8%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #21DeepSeek V4.1 Flash11.6%
- ~#22Qwen3.5 9BEstimated10.8%
- #22Gemini 3.5 Flash-Lite10.2%
No published score — estimated from related benchmarks
Hard reasoning
Humanity's Last ExamVerified
#92 of 19814.9%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #91Trinity Large Thinking15.8%
- #92Qwen3.5 9B14.9%
- #92Qwen3.5 Omni Plus14.9%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#23 of 34 (estimated)~75.5%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #22Phi-4-reasoning-plus78.0%
- ~#23Qwen3.5 9BEstimated75.5%
- #23Mistral Large 338.0%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#23 of 11986.8%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #22HyperCLOVA X SEED Think (32B)87.4%
- #23Qwen3.5 9B86.8%
- #24GPT-5.6 Terra86.3%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~62.5%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12Qwen3.5 9BEstimated62.5%
- #12Nemotron 3.5 Super VL NVFP452.3%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompEstimated
~#19 of 22 (estimated)~59.5%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19Qwen3.5 9BEstimated59.5%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#77 of 91407 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #76HyperNova 60B 2605428
- #77Qwen3.5 9B407
- #78Mistral Large 3406
artificialanalysis.ai · 2026-09-24
AutomationBench-AAEstimated
~#47 of 85 (estimated)~9.7%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #46K2 Horizon 3.7B14.7%
- ~#47Qwen3.5 9BEstimated9.7%
- #47Qwen3.5 397B A17B6.9%
No published score — estimated from related benchmarks