Skip to content
Model Pareto

Kimi Linear 48B A3B Instruct

Moonshot AI (Kimi)Open weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~96tok/sest.
Context
1Mtokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Kimi Linear 48B A3B Instruct. 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
1× H200 141GB
FP8 weights
Throughput
~7,486 tok/s
many requests batched
Price
$0.051–0.42 /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)
  • FP8 weights (48B params, 3B active per token) + 40% KV-cache headroom ≈ 67 GB
  • 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~7,486 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~155,846 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

MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. #4gpt-oss-120b81.3%
  4. ~#5Kimi Linear 48B A3B InstructEstimated<81.3%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#52 of 54 (estimated)~1280 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #51NVIDIA Nemotron 3 Nano 30B A3B1286
  4. ~#52Kimi Linear 48B A3B InstructEstimated1280
  5. #52Phi-41233
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#52 of 54 (estimated)~1309 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #51NVIDIA Nemotron 3 Nano 30B A3B1314
  4. ~#52Kimi Linear 48B A3B InstructEstimated1309
  5. #52Olmo 3.1 32B Think1286
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#21 of 25 (estimated)~21.7%
  1. #1Inkling97.1%
  2. #2Muse Glimmer94.7%
  3. #20Ministral 3 3B22.0%
  4. ~#21Kimi Linear 48B A3B InstructEstimated21.7%
  5. #21Llama 4 Maverick19.3%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#75 of 75 (estimated)~2.7
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
  3. #74K2 Horizon 0.9B3.0
  4. ~#75Kimi Linear 48B A3B InstructEstimated2.7
No published score — estimated from related benchmarks

Agents

OSWorld-VerifiedEstimated
~#11 of 12 (estimated)~62.1%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Muse Glimmer65.9%
  4. ~#11Kimi Linear 48B A3B InstructEstimated62.1%
  5. #11Claude Haiku 4.550.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Kimi Linear 48B A3B InstructEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#57 of 87 (estimated)~613 Elo
  1. #1Claude Opus 5.51846
  2. #2Claude Fable 5.11735
  3. #56Nemotron 3.5 Lightning624
  4. ~#57Kimi Linear 48B A3B InstructEstimated613
  5. #57Gemma 4 31B606
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~last of 89 (estimated)below measured range (<3.3%)
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #88Llama 4 Scout3.3%
  4. ~#89Kimi Linear 48B A3B InstructEstimated<3.3%
No published score — estimated from related benchmarks