Inkling
- Input
- $1.00/M tok
- Output
- $4.05/M tok
- Blended
- $1.762/M tok · 3:1
- Speed
- 184tok/s
- Context
- 1Mtokens
- Cost per task
- ~$1.7/taskest.
Open weights; no first-party per-token API, price is the Artificial Analysis third-party host price.
Rankings
Coding
Mixed#71 / 137rank by quality42.3±5.4quality / 1004/7 benchmarks measuredWriting & chat
Mixed#50 / 162rank by quality61.4±3.6quality / 1004/5 benchmarks measuredVision
Mixed#56 / 98rank by quality50.9±4.1quality / 1004/6 benchmarks measuredHard reasoning
Mixed#64 / 218rank by quality61.1±3.6quality / 1004/4 benchmarks measuredAgents
Mixed#68 / 187rank by quality41.2±4.6quality / 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
- 16× B200 180GB
- FP8 weights
- Throughput
- ~45,766 tok/s
- many requests batched
- Price
- $0.27–2.40 /M tok
- busy → light use
- On your own machine
- Too large
- needs data-center GPUs
Assumptions (5)
- FP8 weights (975B params, 41B active per token) + 40% KV-cache headroom ≈ 1365 GB
- 16× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~45,766 output tok/s aggregate at batch 1541 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~352,646 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
DeepSWE v1.1Estimated
~#38 of 46 (estimated)~47.9%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #37Qwen3.8 Max (0902)51.0%
- ~#38InklingEstimated47.9%
- #38Ripple-65B Preview44.3%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Verified
#46 of 1011.0%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #46Gemini 3.5 Flash-Lite1.0%
- #46Inkling1.0%
- #46Inkling Small1.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#15 of 28 (estimated)~70.3%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #14Maple-Preview75.1%
- ~#15InklingEstimated70.3%
- #15Mistral Small 464.0%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#23 of 26 (estimated)~34.4
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #22Claude Haiku 5.537.3
- ~#23InklingEstimated34.4
- #23Gemini 3.8 Flash33.3
No published score — estimated from related benchmarks
Writing & chat
IFBenchLab-reported
#9 of 13979.8%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #8Nemotron Cascade 2 30B A3B80.4%
- #9Inkling79.8%
- #10Beam 1.0 501B A23B79.6%
thinkingmachines.ai · 2026-07-15
#18 of 251611 Elo
eqbench.com · 2026-09-24
Vision
MMMU-ProVerified
#43 of 8773.5%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #42DeepSeek V4.1 Flash NVFP473.7%
- #43Inkling73.5%
- #44Gemma 4 31B73.4%
artificialanalysis.ai · 2026-09-24
OmniDocBench v1.5Estimated
~#5 of 8 (estimated)~83.2%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#29 of 4712.8%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #29DeepSeek V4.1 Flash12.8%
- #29Inkling12.8%
- #31Qwen3.5 397B A17B12.2%
artificialanalysis.ai · 2026-09-24
ChartographyVerified
#23 of 2410.0%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #22Gemini 3.5 Flash-Lite10.2%
- #23Inkling10.0%
- #24Mistral Large 39.0%
surgehq.ai · 2026-09-24
Hard reasoning
GPQA DiamondVerified
#49 of 19287.2%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #48K2 Horizon 375B A23B87.3%
- #49Inkling87.2%
- #50Nemotron 3 Ultra86.7%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#54 of 19831.9%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #53K2 Horizon 375B A23B32.0%
- #54Inkling31.9%
- #55Nemotron 3.5 Super VL NVFP431.4%
artificialanalysis.ai · 2026-09-24
Agents
τ²-bench (Telecom)Estimated
~#37 of 120 (estimated)~78.3%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #35Qwen3 Coder Next79.5%
- ~#37InklingEstimated78.3%
- #37EXAONE 4.5 33B78.1%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~65.2%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12InklingEstimated65.2%
- #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
BrowseCompLab-reported
#16 of 2177.1%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #15Nemotron 3.5 Super VL NVFP477.5%
- #16Inkling77.1%
- #17Beam 1.0 501B A23B76.8%
thinkingmachines.ai · 2026-07-15
GDPval-AA (Elo)Verified
#37 of 911076 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #36Nex-N2-Pro1091
- #37Inkling1076
- #38Grok Build 0.1 06161052
artificialanalysis.ai · 2026-10-10