Qwen3.5 0.8B
- Input
- —
- Output
- —
- Speed
- ~100tok/sest.
- Context
- 262Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Qwen3.5 0.8B (Non-reasoning). Price = AA median host price.
Rankings
Writing & chat
Verified#155 / 162rank by quality13.3±9.5quality / 1001/5 benchmarks measuredVision
Verified#96 / 98rank by quality11.0±8.2quality / 1001/6 benchmarks measuredHard reasoning
Verified#211 / 218rank by quality7.2±5.9quality / 1002/4 benchmarks measuredAgents
Verified#99 / 187rank by quality29.7±10.0quality / 1001/7 benchmarks measured
Self-hostingEstimated
How we estimate →What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.
- Hardware
- 1× H200 141GB
- BF16 weights
- Throughput
- ~23,090 tok/s
- many requests batched
- Price
- $0.018–0.15 /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)
- BF16 weights (0.8B params) + 25% KV-cache headroom ≈ 2 GB
- 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
- ~23,090 output tok/s aggregate at batch 256 (bandwidth-bound)
- Blended 3:1 input:output; prefill ~292,064 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
#134 of 13921.6%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #133Apertus 8B Instruct22.4%
- #134Qwen3.5 0.8B21.6%
- #135Tiny Aya Global20.1%
artificialanalysis.ai · 2026-09-24
MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#55 of 57 (estimated)~1284 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #54NVIDIA Nemotron 3 Nano 30B A3B1286
- ~#55Qwen3.5 0.8BEstimated1284
- #55Phi-41233
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#55 of 57 (estimated)~1312 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #54NVIDIA Nemotron 3 Nano 30B A3B1314
- ~#55Qwen3.5 0.8BEstimated1312
- #55Olmo 3.1 32B Think1286
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#24 of 26 (estimated)~1353 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #23Gemma 4 31B1368
- ~#24Qwen3.5 0.8BEstimated1353
- #24gpt-oss-120b961
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#85 of 8725.7%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #84LFM2.5-VL-1.6B26.5%
- #85Qwen3.5 0.8B25.7%
- #86Molmo 7B-D24.5%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~last of 12 (estimated)below measured range (<74.5%)
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~last of 8 (estimated)below measured range (<75.8%)
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#46 of 48 (estimated)~0.1%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #45Ministral 3 8B0.8%
- ~#46Qwen3.5 0.8BEstimated0.1%
- #46Ministral 3 3B0.0%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 25 (estimated)below measured range (<9.0%)
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#190 of 19223.6%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #189Molmo 7B-D24.0%
- #190Qwen3.5 0.8B23.6%
- #191Gemma 3 270M22.4%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#158 of 1985.1%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #158Molmo 7B-D5.1%
- #158Qwen3.5 0.8B5.1%
- #162Apertus 8B Instruct5.0%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#30 of 34 (estimated)~20.9%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #29Ministral 3 3B22.0%
- ~#30Qwen3.5 0.8BEstimated20.9%
- #30Llama 4 Maverick19.3%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#99 of 103 (estimated)~5.9
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #98Ministral 3 14B6.0
- ~#99Qwen3.5 0.8BEstimated5.9
- #99Ministral 3 8B5.5
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#45 of 11965.2%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #44gpt-oss-120b65.8%
- #45Qwen3.5 0.8B65.2%
- #46HyperNova 60B 260563.2%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~54.5%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12Qwen3.5 0.8BEstimated54.5%
- #12Nemotron 3.5 Super VL NVFP452.3%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#19 of 22 (estimated)~53.3%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19Qwen3.5 0.8BEstimated53.3%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#50 of 92 (estimated)~852 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #49LongCat 2.0856
- ~#50Qwen3.5 0.8BEstimated852
- #50Step 3.7 Flash845
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#62 of 85 (estimated)~2.2%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #61Mercury 2.52.4%
- ~#62Qwen3.5 0.8BEstimated2.2%
- #62Granite 4.2 8B2.1%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#83 of 91 (estimated)~4.8%
- #1Muse Spark 1.350.5%
- #2GLM-5.350.3%
- #81Mistral Small 44.9%
- ~#83Qwen3.5 0.8BEstimated4.8%
- #83Ministral 3 3B4.7%
No published score — estimated from related benchmarks