Skip to content
Model Pareto

LFM2.5-2.6B

Liquid AIOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~120tok/sest.
Context
128Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: LFM2.5-2.6B. 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
BF16 weights
Throughput
~19,533 tok/s
many requests batched
Price
$0.037–0.33 /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 (2.69B params) + 25% KV-cache headroom ≈ 7 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~19,533 output tok/s aggregate at batch 256 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~197,607 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

SWE-bench VerifiedEstimated
~last of 14 (estimated)below measured range (<62.4%)
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. #13gpt-oss-120b62.4%
  4. ~#14LFM2.5-2.6BEstimated<62.4%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~last of 19 (estimated)below measured range (<43.8%)
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #18Nex-N2.5-Mini43.8%
  4. ~#19LFM2.5-2.6BEstimated<43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#30 of 31 (estimated)~28.0%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #29Nex-N2.5-Mini36.1%
  4. ~#30LFM2.5-2.6BEstimated28.0%
  5. #30Hy328.0%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Estimated
~#49 of 84 (estimated)~0.1%
  1. #1Claude Sonnet 5.563.6%
  2. #2Claude Opus 5.559.6%
  3. #39Trinity Large Thinking0.5%
  4. ~#49LFM2.5-2.6BEstimated0.1%
  5. #49Apodex 1.10.0%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#19 of 20 (estimated)~25.7%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #18Llama 4 Scout29.9%
  4. ~#19LFM2.5-2.6BEstimated25.7%
  5. #19Ministral 3 3B24.7%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~last of 15 (estimated)below measured range (<41.1)
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #14GPT-6 Luna41.1
  4. ~#15LFM2.5-2.6BEstimated<41.1
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#14 of 25 (estimated)~42.5%
  1. #1Inkling97.1%
  2. #2Muse Glimmer94.7%
  3. #13Phi-4-reasoning-plus78.0%
  4. ~#14LFM2.5-2.6BEstimated42.5%
  5. #14Mistral Large 338.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#70 of 75 (estimated)~6.3
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
  3. #69Devstral Small 27.5
  4. ~#70LFM2.5-2.6BEstimated6.3
  5. #70Celeris-16.3
No published score — estimated from related benchmarks

Agents

τ²-bench (Telecom)Estimated
~#54 of 116 (estimated)~34.6%
  1. #1Step 3.7 Flash98.5%
  2. #2Gemini 3.1 Pro95.6%
  3. #53North Mini Code37.4%
  4. ~#54LFM2.5-2.6BEstimated34.6%
  5. #54Sarvam 30B34.5%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#11 of 12 (estimated)~58.3%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Muse Glimmer65.9%
  4. ~#11LFM2.5-2.6BEstimated58.3%
  5. #11Claude Haiku 4.550.7%
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. ~#5LFM2.5-2.6BEstimated<47.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#15 of 18 (estimated)~48.8%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #14Inkling77.1%
  4. ~#15LFM2.5-2.6BEstimated48.8%
  5. #15Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#63 of 87 (estimated)~504 Elo
  1. #1Claude Opus 5.51846
  2. #2Claude Fable 5.11735
  3. #62Devstral Small 2516
  4. ~#63LFM2.5-2.6BEstimated504
  5. #63Qwen3 Coder Next501
No published score — estimated from related benchmarks