Skip to content
Model Pareto

K2 Think V2

MBZUAI Institute of Foundation ModelsOpen weightsartificialanalysis.ai ↗
Input
—
Output
—
Speed
~84tok/sest.
Context
262Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: K2 Think V2. 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× B200 180GB
FP8 weights
Throughput
~2,239 tok/s
many requests batched
Price
$0.36–3.22 /M tok
busy → light use
On your own machine
Mac Studio M5 Max 128GB (int4, ~12 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (72.5B params) + 25% KV-cache headroom ≈ 91 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~2,239 output tok/s aggregate at batch 64 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~14,664 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

Hard reasoning

Agents

~#12 of 15 (estimated)~60.5%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #11Muse Glimmer65.9%
  4. ~#12K2 Think V2Estimated60.5%
  5. #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%)
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #4GPT-5.547.5%
  4. ~#5K2 Think V2Estimated<47.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#19 of 22 (estimated)~49.6%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #18Nemotron 3.5 Bolt 74B-A9B70.0%
  4. ~#19K2 Think V2Estimated49.6%
  5. #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
~#47 of 85 (estimated)~12.1%
  1. #1Claude Fable 5.276.4%
  2. #2Muse Wonder Full71.3%
  3. #46K2 Horizon 3.7B14.7%
  4. ~#47K2 Think V2Estimated12.1%
  5. #47Qwen3.5 397B A17B6.9%
No published score — estimated from related benchmarks
~#53 of 91 (estimated)~13.7%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #52Nemotron 3 Ultra14.2%
  4. ~#53K2 Think V2Estimated13.7%
  5. #53Grok Build 0.1 061613.4%
No published score — estimated from related benchmarks