LFM2.5-VL-1.6B
- Input
- —
- Output
- —
- Speed
- ~120tok/sest.
- Context
- 32Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: LFM2.5-VL-1.6B. Price = AA median host price.
Rankings
Writing & chat
Verified#142 / 162rank by quality18.5±9.5quality / 1001/5 benchmarks measuredVision
Verified#95 / 98rank by quality11.4±8.2quality / 1001/6 benchmarks measuredHard reasoning
Verified#208 / 218rank by quality8.0±5.9quality / 1002/4 benchmarks measuredAgents
Verified#176 / 187rank by quality12.3±10.0quality / 1001/7 benchmarks measured
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
- ~16,055 tok/s
- many requests batched
- Price
- $0.028–0.23 /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 (1.6B params) + 25% KV-cache headroom ≈ 4 GB
- 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
- ~16,055 output tok/s aggregate at batch 256 (bandwidth-bound)
- Blended 3:1 input:output; prefill ~146,032 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
#106 of 13933.1%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #105Qwen3.5 4B33.3%
- #106LFM2.5-VL-1.6B33.1%
- #107Olmo 3 7B Instruct32.8%
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
~#54 of 57 (estimated)~1290 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #53Ring-flash-2.0Few votes1293
- ~#54LFM2.5-VL-1.6BEstimated1290
- #54NVIDIA Nemotron 3 Nano 30B A3B1286
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#53 of 57 (estimated)~1317 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #52Ring-flash-2.01321
- ~#53LFM2.5-VL-1.6BEstimated1317
- #53gpt-oss-20b1317
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#23 of 26 (estimated)~1383 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #22Mistral Large 31412
- ~#23LFM2.5-VL-1.6BEstimated1383
- #23Gemma 4 31B1368
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#84 of 8726.5%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #83Llama 3.2 Instruct 11B (Vision)29.3%
- #84LFM2.5-VL-1.6B26.5%
- #85Qwen3.5 0.8B25.7%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~last of 12 (estimated)below measured range (<74.5%)
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~last of 8 (estimated)below measured range (<75.8%)
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#46 of 48 (estimated)~0.1%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #45Ministral 3 8B0.8%
- ~#46LFM2.5-VL-1.6BEstimated0.1%
- #46Ministral 3 3B0.0%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 25 (estimated)below measured range (<9.0%)
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#182 of 19228.9%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #181K2 Horizon 0.9B29.3%
- #182LFM2.5-VL-1.6B28.9%
- #183MiniCPM5-1B27.8%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#158 of 1985.1%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #157Tiny Aya Global5.2%
- #158LFM2.5-VL-1.6B5.1%
- #158MiniCPM-V 4.6 1.3B5.1%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#30 of 34 (estimated)~19.4%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #29Ministral 3 3B22.0%
- ~#30LFM2.5-VL-1.6BEstimated19.4%
- #30Llama 4 Maverick19.3%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#102 of 103 (estimated)~4.6
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #100NVIDIA Nemotron 3 Nano 4B4.8
- ~#102LFM2.5-VL-1.6BEstimated4.6
- #102K2 Horizon 0.9B3.0
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#108 of 1198.5%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #107Gemma 3 270M9.1%
- #108LFM2.5-VL-1.6B8.5%
- #109EXAONE 4.0 32B4.1%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#13 of 15 (estimated)~51.2%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #12Nemotron 3.5 Super VL NVFP452.3%
- ~#13LFM2.5-VL-1.6BEstimated51.2%
- #13Nemotron 3.5 Super VL51.1%
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)~34.2%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21LFM2.5-VL-1.6BEstimated34.2%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#61 of 92 (estimated)~660 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #60MiniCPM5-2B694
- ~#61LFM2.5-VL-1.6BEstimated660
- #61Nemotron 3.5 Lightning624
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#79 of 85 (estimated)~0.2%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #77Granite 4.2 3B0.4%
- ~#79LFM2.5-VL-1.6BEstimated0.2%
- #79gpt-oss-120b0.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~last of 91 (estimated)below measured range (<3.3%)
No published score — estimated from related benchmarks