Qwen3.5 122B A10B
- Input
- $0.40/M tok
- Output
- $3.20/M tok
- Blended
- $1.10/M tok · 3:1
- Speed
- 129tok/s
- Context
- 262Ktokens
- Cost per task
- ~$1.4/taskest.
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Qwen3.5 122B A10B (Reasoning). Price = AA median host price.
Rankings
Coding
Verified#99 / 137rank by quality33.8±8.1quality / 1002/7 benchmarks measuredWriting & chat
Verified#62 / 162rank by quality56.5±4.1quality / 1003/5 benchmarks measuredVision
Verified#65 / 98rank by quality45.5±6.3quality / 1002/6 benchmarks measuredHard reasoning
Verified#94 / 218rank by quality49.1±3.7quality / 1003/4 benchmarks measuredAgents
Verified#85 / 187rank by quality36.7±4.3quality / 1004/7 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
- 4× H100 80GB
- FP8 weights
- Throughput
- ~10,951 tok/s
- many requests batched
- Price
- $0.11–1.03 /M tok
- busy → light use
- On your own machine
- Mac Studio M5 Max 128GB (int4, ~86 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- FP8 weights (122B params, 10B active per token) + 25% KV-cache headroom ≈ 153 GB
- 4× H100 80GB at $2.69–$6.88/GPU-hour on-demand (2026-09-24)
- ~10,951 output tok/s aggregate at batch 320 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~187,016 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
~#16 of 21 (estimated)~70.9%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #15Nemotron 3.5 Super VL NVFP471.1%
- ~#16Qwen3.5 122B A10BEstimated70.9%
- #16Nemotron 3 Ultra70.7%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#23 of 24 (estimated)~50.1%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #22Muse Glimmer51.2%
- ~#23Qwen3.5 122B A10BEstimated50.1%
- #23Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#38 of 46 (estimated)~44.7%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #37Qwen3.8 Max (0902)51.0%
- ~#38Qwen3.5 122B A10BEstimated44.7%
- #38Ripple-65B Preview44.3%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Verified
#63 of 1010.0%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #63Qwen3 Coder Next0.0%
- #63Qwen3.5 122B A10B0.0%
- #63Qwen3.5 397B A17B0.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#16 of 28 (estimated)~63.5%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #15Mistral Small 464.0%
- ~#16Qwen3.5 122B A10BEstimated63.5%
- #16Claude Haiku 4.561.5%
No published score — estimated from related benchmarks
SciCodeVerified
#82 of 11839.7%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #82Nemotron 3.5 Bolt 74B-A9B39.7%
- #82Qwen3.5 122B A10B39.7%
- #84Intern-S2-Preview (35B-A3B)39.6%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#25 of 26 (estimated)~30.6
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #24GPT-6 Luna31.1
- ~#25Qwen3.5 122B A10BEstimated30.6
- #25Muse Spark Open26.3
No published score — estimated from related benchmarks
Writing & chat
IFBenchVerified
#22 of 13975.7%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #20GPT-5.575.9%
- #22Qwen3.5 122B A10B75.7%
- #23Gemma 4 31B75.6%
artificialanalysis.ai · 2026-09-24
LMArena Text, Non-English (Elo)Verified
#39 of 561397 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #39Mistral Large 31397
- #39Qwen3.5 122B A10B1397
- #41Claude Haiku 4.51395
lmarena.ai · 2026-09-13
LMArena Text (Elo)Verified
#39 of 561417 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #38Muse GlimmerFew votes1424
- #39Qwen3.5 122B A10B1417
- #40Claude Haiku 4.51415
lmarena.ai · 2026-09-13
EQ-Bench Creative Writing v3 (Elo)Estimated
~#17 of 26 (estimated)~1691 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #16Nemotron 3 Ultra1692
- ~#17Qwen3.5 122B A10BEstimated1691
- #17Qwen3.8 27B1671
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#37 of 8775.0%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #36Step 3.7 Flash75.3%
- #37Qwen3.5 122B A10B75.0%
- #37Qwen3.6 35B A3B75.0%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~#11 of 12 (estimated)~76.1%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #10Claude Sonnet 577.0%
- ~#11Qwen3.5 122B A10BEstimated76.1%
- #11Gemini 3.5 Flash-Lite74.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#5 of 8 (estimated)~81.8%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #4Gemini 3.1 Pro85.3%
- ~#5Qwen3.5 122B A10BEstimated81.8%
- #5Claude Haiku 4.579.6%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#39 of 473.4%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #38Claude Haiku 4.53.8%
- #39Qwen3.5 122B A10B3.4%
- #40Mistral Medium 3.52.8%
artificialanalysis.ai · 2026-09-24
ChartographyEstimated
~#21 of 25 (estimated)~11.7%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #20Grok 4.714.7%
- ~#21Qwen3.5 122B A10BEstimated11.7%
- #21DeepSeek V4.1 Flash11.6%
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#53 of 19285.7%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #53Gemma 4 31B85.7%
- #53Qwen3.5 122B A10B85.7%
- #53Ring-2.6-1T85.7%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#66 of 19825.2%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #65Solar Mini 425.8%
- #66Qwen3.5 122B A10B25.2%
- #67Nemotron 3.5 Bolt 74B-A9B24.7%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#19 of 34 (estimated)~86.3%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #18Mistral Medium 3.586.3%
- ~#19Qwen3.5 122B A10BEstimated86.3%
- #19Mistral Small 484.0%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#8 of 11993.6%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #7GPT-5.593.9%
- #8Qwen3.5 122B A10B93.6%
- #9Qwen3.7 Plus93.0%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~64.6%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12Qwen3.5 122B A10BEstimated64.6%
- #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)~63.4%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19Qwen3.5 122B A10BEstimated63.4%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#51 of 91802 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #50Step 3.7 Flash845
- #51Qwen3.5 122B A10B802
- #52Muse Glimmer786
artificialanalysis.ai · 2026-09-24