LFM2.5-8B-A1B
- Input
- —
- Output
- —
- Speed
- ~120tok/sest.
- Context
- 33Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: LFM2.5-8B-A1B. 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
- ~13,288 tok/s
- many requests batched
- Price
- $0.031–0.26 /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 (8.3B params, 1.5B active per token) + 25% KV-cache headroom ≈ 21 GB
- 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
- ~13,288 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~155,768 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
IFBenchVerified
#66 of 13955.6%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #65Trinity Large Thinking56.3%
- #66LFM2.5-8B-A1B55.6%
- #67Tri-21B-Think54.6%
artificialanalysis.ai · 2026-09-24
MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#46 of 57 (estimated)~1339 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #45Trinity Large Thinking1350
- ~#46LFM2.5-8B-A1BEstimated1339
- #46gpt-oss-120b1338
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#46 of 57 (estimated)~1360 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #45Trinity Large Thinking1369
- ~#46LFM2.5-8B-A1BEstimated1360
- #46INTELLECT-31356
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#19 of 26 (estimated)~1566 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #18Inkling1611
- ~#19LFM2.5-8B-A1BEstimated1566
- #19Gemini 3.5 Flash-Lite1559
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#153 of 19251.3%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #152Olmo 3 7B Think51.6%
- #153LFM2.5-8B-A1B51.3%
- #153NVIDIA Nemotron 3 Nano 4B51.3%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#134 of 1986.9%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #133Nova 2.0 Omni7.0%
- #134LFM2.5-8B-A1B6.9%
- #135Celeris-16.8%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#23 of 34 (estimated)~39.8%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #22Phi-4-reasoning-plus78.0%
- ~#23LFM2.5-8B-A1BEstimated39.8%
- #23Mistral Large 338.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#96 of 103 (estimated)~6.6
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #95Devstral Small 27.5
- ~#96LFM2.5-8B-A1BEstimated6.6
- #96Llama 4 Scout6.5
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#89 of 11916.1%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #88Qwen3 Omni 30B A3B Instruct16.4%
- #89LFM2.5-8B-A1B16.1%
- #89Step3 VL 10B16.1%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~52.9%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12LFM2.5-8B-A1BEstimated52.9%
- #12Nemotron 3.5 Super VL NVFP452.3%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#21 of 22 (estimated)~35.4%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21LFM2.5-8B-A1BEstimated35.4%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#60 of 92 (estimated)~716 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #59Claude Haiku 4.5719
- ~#60LFM2.5-8B-A1BEstimated716
- #60MiniCPM5-2B694
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#79 of 85 (estimated)~0.3%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #77Granite 4.2 3B0.4%
- ~#79LFM2.5-8B-A1BEstimated0.3%
- #79gpt-oss-120b0.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#81 of 91 (estimated)~5.4%
- #1Muse Spark 1.350.5%
- #2GLM-5.350.3%
- #80Qwen3 Coder Next5.4%
- ~#81LFM2.5-8B-A1BEstimated5.4%
- #81K2 Horizon 0.9B4.9%
No published score — estimated from related benchmarks