Skip to content
Model Pareto

LFM2 24B A2B

Liquid AIOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~120tok/sest.
Context
33Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: LFM2 24B A2B. 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
BF16 weights
Throughput
~8,092 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)
  • BF16 weights (24B params, 2.3B active per token) + 25% KV-cache headroom ≈ 60 GB
  • 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~8,092 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~101,588 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. ~#5LFM2 24B A2BEstimated<81.3%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#45 of 54 (estimated)~1316 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #44INTELLECT-3Few votes1327
  4. ~#45LFM2 24B A2BEstimated1316
  5. #45Llama 4 Maverick1311
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#46 of 54 (estimated)~1340 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #45Llama 3.1 Nemotron Ultra 253B v1Few votes1348
  4. ~#46LFM2 24B A2BEstimated1340
  5. #46Olmo 3.1 32B Instruct1330
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#18 of 25 (estimated)~31.7%
  1. #1Inkling97.1%
  2. #2Muse Glimmer94.7%
  3. #17Phi-4-mini-flash-reasoning33.6%
  4. ~#18LFM2 24B A2BEstimated31.7%
  5. #18Ministral 3 8B31.7%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#74 of 75 (estimated)~4.7
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
  3. #73Ministral 3 3B4.8
  4. ~#74LFM2 24B A2BEstimated4.7
  5. #74K2 Horizon 0.9B3.0
No published score — estimated from related benchmarks

Agents

OSWorld-VerifiedEstimated
~#11 of 12 (estimated)~63.1%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Muse Glimmer65.9%
  4. ~#11LFM2 24B A2BEstimated63.1%
  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. ~#3LFM2 24B A2BEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#17 of 18 (estimated)~31.7%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #16Nemotron 3 Ultra44.4%
  4. ~#17LFM2 24B A2BEstimated31.7%
  5. #17Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#56 of 87 (estimated)~681 Elo
  1. #1Claude Opus 5.51846
  2. #2Claude Fable 5.11735
  3. #55MiniCPM5-2B694
  4. ~#56LFM2 24B A2BEstimated681
  5. #56Nemotron 3.5 Lightning624
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#74 of 80 (estimated)~0.3%
  1. #1Claude Opus 5.569.5%
  2. #2DeepSeek V4.1 Flash68.9%
  3. #72Granite 4.2 3B0.4%
  4. ~#74LFM2 24B A2BEstimated0.3%
  5. #74gpt-oss-120b0.2%
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. ~#89LFM2 24B A2BEstimated<3.3%
No published score — estimated from related benchmarks