LFM2.5-1.2B-Thinking
- Input
- —
- Output
- —
- Speed
- ~130tok/sest.
- Context
- 32Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: LFM2.5-1.2B-Thinking. 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
- ~18,931 tok/s
- many requests batched
- Price
- $0.023–0.19 /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 (1.17B params) + 25% KV-cache headroom ≈ 3 GB
- 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
- ~18,931 output tok/s aggregate at batch 256 (bandwidth-bound)
- Blended 3:1 input:output; prefill ~199,702 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
#86 of 13941.8%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #85Llama 4 Maverick43.0%
- #86LFM2.5-1.2B-Thinking41.8%
- #87Olmo 3 7B Think41.5%
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
~#50 of 57 (estimated)~1306 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #49Llama 3.1 Nemotron Ultra 253B v1Few votes1306
- ~#50LFM2.5-1.2B-ThinkingEstimated1306
- #50Molmo2-8BFew votes1305
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#49 of 57 (estimated)~1331 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #48Llama 3.1 Nemotron Ultra 253B v1Few votes1348
- ~#49LFM2.5-1.2B-ThinkingEstimated1331
- #49Olmo 3.1 32B Instruct1330
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#22 of 26 (estimated)~1487 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #21Gemini 3.1 Pro1491
- ~#22LFM2.5-1.2B-ThinkingEstimated1487
- #22Mistral Large 31412
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#173 of 19233.9%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #171Nova Micro35.8%
- #173LFM2.5-1.2B-Thinking33.9%
- #174Granite 4.0 Micro33.6%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#143 of 1986.2%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #141Olmo 3.1 32B Think6.3%
- #143LFM2.5-1.2B-Thinking6.2%
- #143LFM2.5-2.6B6.2%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#30 of 34 (estimated)~20.4%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #29Ministral 3 3B22.0%
- ~#30LFM2.5-1.2B-ThinkingEstimated20.4%
- #30Llama 4 Maverick19.3%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#99 of 103 (estimated)~5.8
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #98Ministral 3 14B6.0
- ~#99LFM2.5-1.2B-ThinkingEstimated5.8
- #99Ministral 3 8B5.5
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#84 of 11919.6%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #84Granite 4.0 H 1B19.6%
- #84LFM2.5-1.2B-Thinking19.6%
- #86Llama 4 Maverick17.8%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#13 of 15 (estimated)~51.7%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #12Nemotron 3.5 Super VL NVFP452.3%
- ~#13LFM2.5-1.2B-ThinkingEstimated51.7%
- #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)~33.8%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21LFM2.5-1.2B-ThinkingEstimated33.8%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#58 of 92 (estimated)~729 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #57Ring-2.6-1T734
- ~#58LFM2.5-1.2B-ThinkingEstimated729
- #58KAT Coder Pro V2720
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%
- ~#79LFM2.5-1.2B-ThinkingEstimated0.3%
- #79gpt-oss-120b0.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#91 of 91 (estimated)~3.2%
No published score — estimated from related benchmarks