Motif 3
- Input
- —
- Output
- —
- Speed
- ~92tok/sest.
- Context
- 262Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Motif 3. Price = AA median host price.
Rankings
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
- 4× B200 180GB
- FP8 weights
- Throughput
- ~19,600 tok/s
- many requests batched
- Price
- $0.13–1.19 /M tok
- busy → light use
- On your own machine
- Mac Studio M5 Ultra 512GB (int4, ~130 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- FP8 weights (314B params, 13.2B active per token) + 25% KV-cache headroom ≈ 393 GB
- 4× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~19,600 output tok/s aggregate at batch 561 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~322,159 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
~#14 of 21 (estimated)~72.8%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #13Claude Haiku 4.573.3%
- ~#14Motif 3Estimated72.8%
- #14Nemotron 3.5 Super VL71.1%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#20 of 24 (estimated)~52.8%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #18Gemini 3.5 Flash-Lite54.2%
- ~#20Motif 3Estimated52.8%
- #20Nemotron 3.5 Super VL51.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#39 of 46 (estimated)~43.4%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #38Ripple-65B Preview44.3%
- ~#39Motif 3Estimated43.4%
- #39Beam 1.0 501B A23B43.3%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Estimated
~#34 of 102 (estimated)~14.5%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #33GPT-5.514.6%
- ~#34Motif 3Estimated14.5%
- #34Claude Sonnet 514.1%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#15 of 28 (estimated)~70.9%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #14Maple-Preview75.1%
- ~#15Motif 3Estimated70.9%
- #15Mistral Small 464.0%
No published score — estimated from related benchmarks
SciCodeVerified
#71 of 11842.2%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #71Claude Haiku 4.542.2%
- #71Motif 342.2%
- #73K-EXAONE 2.0 080342.0%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#23 of 26 (estimated)~35.1
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #22Claude Haiku 5.537.3
- ~#23Motif 3Estimated35.1
- #23Gemini 3.8 Flash33.3
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#66 of 19283.4%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #65Muse Glimmer83.5%
- #66Motif 383.4%
- #67K-EXAONE 2.0 080382.9%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#41 of 19837.0%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #40Qwen3.8 Flash-Next38.0%
- #41Motif 337.0%
- #42Qwen3.8-Omni-Flash36.5%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#9 of 34 (estimated)~93.0%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #8gpt-oss-120b93.4%
- ~#9Motif 3Estimated93.0%
- #9Qwen3.8 27B MXFP492.5%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#38 of 103 (estimated)~32.0
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #37Qwen3.8 27B33.7
- ~#38Motif 3Estimated32.0
- #38K2 Horizon 375B A23B30.5
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#12 of 120 (estimated)~91.9%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #11Ring-2.6-1T92.4%
- ~#12Motif 3Estimated91.9%
- #12MiMo-V2.590.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#9 of 15 (estimated)~76.2%
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
~#14 of 22 (estimated)~82.8%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #13Nex-N2.5-Mini83.4%
- ~#14Motif 3Estimated82.8%
- #14Nemotron 3.5 Super VL78.0%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#21 of 92 (estimated)~1501 Elo
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#29 of 85 (estimated)~39.5%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #28GPT-5.547.3%
- ~#29Motif 3Estimated39.5%
- #29K2 Horizon 375B A23B37.2%
No published score — estimated from related benchmarks