Skip to content
Model Pareto

Ling-2.6-1T

inclusionAI (Ant Group)Open weightsartificialanalysis.ai ↗
Input
$0.30/M tok
Output
$2.50/M tok
Blended
$0.85/M tok · 3:1
Speed
~100tok/sest.
Context
262Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Ling-2.6-1T. Price = AA median host price.

Rankings

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× H200 141GB
FP8 weights
Throughput
~21,013 tok/s
many requests batched
Price
$0.38–3.13 /M tok
busy → light use
On your own machine
Too large
needs data-center GPUs
Assumptions (5)
  • FP8 weights (1000B params, 50B active per token) + 25% KV-cache headroom ≈ 1250 GB
  • 16× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~21,013 output tok/s aggregate at batch 889 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~127,171 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

~#11 of 15 (estimated)~67.4%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Nex-N2.5-Mini71.2%
  4. ~#11Ling-2.6-1TEstimated67.4%
  5. #11Muse Glimmer65.9%
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. ~#3Ling-2.6-1TEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#18 of 22 (estimated)~70.6%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #17Beam 1.0 501B A23B76.8%
  4. ~#18Ling-2.6-1TEstimated70.6%
  5. #18Nemotron 3.5 Bolt 74B-A9B70.0%
No published score — estimated from related benchmarks
~#47 of 92 (estimated)~927 Elo
  1. #1Claude Opus 5.51866
  2. #2Muse Wonder Full1857
  3. #46GPT-5.4 nano937
  4. ~#47Ling-2.6-1TEstimated927
  5. #47Qwen3.6 35B A3B879
No published score — estimated from related benchmarks
~#47 of 85 (estimated)~12.2%
  1. #1Claude Fable 5.276.4%
  2. #2Muse Wonder Full71.3%
  3. #46K2 Horizon 3.7B14.7%
  4. ~#47Ling-2.6-1TEstimated12.2%
  5. #47Qwen3.5 397B A17B6.9%
No published score — estimated from related benchmarks
~#51 of 91 (estimated)~14.4%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #50Gemma 4 31B14.8%
  4. ~#51Ling-2.6-1TEstimated14.4%
  5. #51Granite 4.2 30B14.4%
No published score — estimated from related benchmarks