Step3 VL 10B
- Input
- —
- Output
- —
- Speed
- ~100tok/sest.
- Context
- 66Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Step3 VL 10B. Price = AA median host price.
Rankings
Writing & chat
Verified#86 / 162rank by quality39.7±9.5quality / 1001/5 benchmarks measuredVision
Verified#69 / 98rank by quality38.4±8.2quality / 1001/6 benchmarks measuredHard reasoning
Verified#135 / 218rank by quality34.5±5.9quality / 1002/4 benchmarks measuredAgents
Verified#121 / 187rank by quality22.4±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× B200 180GB
- BF16 weights
- Throughput
- ~9,402 tok/s
- many requests batched
- Price
- $0.091–0.81 /M tok
- busy → light use
- On your own machine
- RTX 5090 32GB (int4, ~250 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- BF16 weights (10.17B params) + 25% KV-cache headroom ≈ 25 GB
- 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~9,402 output tok/s aggregate at batch 256 (bandwidth-bound)
- Blended 3:1 input:output; prefill ~52,268 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
#73 of 13950.2%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #72Qwen3.5 Omni Plus51.2%
- #73Step3 VL 10B50.2%
- #74MiniCPM5-1B49.3%
artificialanalysis.ai · 2026-09-24
MMMLUEstimated
~#4 of 5 (estimated)~81.9%
- #1Gemini 3.1 Pro92.6%
- #2Gemma 4 31B88.4%
- #3Claude Haiku 4.583.0%
- ~#4Step3 VL 10BEstimated81.9%
- #4gpt-oss-120b81.3%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#44 of 57 (estimated)~1371 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #43Qwen3 Next 80B A3B Instruct1386
- ~#44Step3 VL 10BEstimated1371
- #44GLM-4.6VFew votes1361
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#44 of 57 (estimated)~1390 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #43Qwen3 Next 80B A3B Instruct1399
- ~#44Step3 VL 10BEstimated1390
- #44GLM-4.6VFew votes1378
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#21 of 26 (estimated)~1493 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #20DeepSeek V4.1 Flash1540
- ~#21Step3 VL 10BEstimated1493
- #21Gemini 3.1 Pro1491
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#56 of 8764.0%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #55Nova 2.0 Pro Preview64.5%
- #56Step3 VL 10B64.0%
- #57Nova 2.0 Lite63.8%
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
~#6 of 8 (estimated)~79.2%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #5Claude Haiku 4.579.6%
- ~#6Step3 VL 10BEstimated79.2%
- #6Mistral Small 476.4%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#37 of 48 (estimated)~6.7%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #36GPT-5.4 nano7.8%
- ~#37Step3 VL 10BEstimated6.7%
- #37Qwen3.6 35B A3B6.6%
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
#115 of 19269.0%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #114K2 Horizon 3.7B69.2%
- #115Step3 VL 10B69.0%
- #116Phi-4-reasoning-plus68.9%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#112 of 19810.8%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #112DiffusionGemma 26B A4B10.8%
- #112Step3 VL 10B10.8%
- #115Nemotron 3.5 Lightning10.6%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#23 of 34 (estimated)~63.2%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #22Phi-4-reasoning-plus78.0%
- ~#23Step3 VL 10BEstimated63.2%
- #23Mistral Large 338.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#74 of 103 (estimated)~13.8
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #73Mistral Medium 3.514.2
- ~#74Step3 VL 10BEstimated13.8
- #74Command A+13.1
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#89 of 11916.1%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #89LFM2.5-8B-A1B16.1%
- #89Step3 VL 10B16.1%
- #91Jamba Reasoning 3B15.8%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~56.7%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12Step3 VL 10BEstimated56.7%
- #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
~#21 of 22 (estimated)~41.1%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21Step3 VL 10BEstimated41.1%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#38 of 92 (estimated)~1052 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #37Inkling1076
- ~#38Step3 VL 10BEstimated1052
- #38Grok Build 0.1 06161052
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#47 of 85 (estimated)~10.8%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #46K2 Horizon 3.7B14.7%
- ~#47Step3 VL 10BEstimated10.8%
- #47Qwen3.5 397B A17B6.9%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#57 of 91 (estimated)~12.6%
- #1Muse Spark 1.350.5%
- #2GLM-5.350.3%
- #56gpt-oss-120b12.8%
- ~#57Step3 VL 10BEstimated12.6%
- #57Gemma 4 26B A4B12.0%
No published score — estimated from related benchmarks