How many benchmarks has LFM2.5-1.2B-Instruct been measured on?

LFM2.5-1.2B-Instruct carries 34 distinct benchmarks on the Vector Wire tracker across 44 recorded measurements, each with its source, harness and verification tier.

Who makes LFM2.5-1.2B-Instruct?

LFM2.5-1.2B-Instruct is a Liquid AI model.

Refresh Models —Deals —Regulatory —Sources —

Basis

Liquid AI·MODEL DOSSIER·TRACKED 44D AGO·LAST SEEN 12D AGO

LFM2.5-1.2B-Instruct

unknown

Limited on Instruction Following. Insufficient data on 9 of 10 axes.

Aliases:lfm-2.5-1.2b-instruct:freelfm2.5-1.2b-instruct-dsparklfm2-5-1-2b-instruct (Non-Reasoning)lfm2-5-1-2b-instruct

Last seen12d agoTracked since44d agoBenchmarks44Pricing rows0Provenance1

1 Limited9 Insufficient

CAPABILITY CLASSIFICATION10 axes

VS AXIS LEADER · BAR = 100 − DISTANCE · ROWS EXPAND TO THEIR EVIDENCE

PRICING

No pricing rows tracked for this entity yet.

RECEIPTS — ALL MEASURED BENCHMARKS44

Benchmark	Score	Settings	Source	Verification	Methodology	Measured	Reference
OmniScience Non-Hallucination omniscienceNonHallucination	14.91	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	4h ago	view ↗
AA Intelligence aa_intelligence_index	2.30	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	4h ago	view ↗
AA-LCR aa_lcr	0.00	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	4h ago	view ↗
AA-Omniscience aa_omniscience	-72.10	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	4h ago	view ↗
IFBench aa_ifbench	43.81	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	4h ago	view ↗
τ²-Bench Telecom (AA run) aa_tau2	10.82	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	4h ago	view ↗
Terminal-Bench Hard aa_terminalbench_hard	0.00	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	4h ago	view ↗
GPQA Diamond gpqa	32.63	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	4h ago	view ↗
OmniScience Accuracy omniscienceAccuracy	7.02	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	4h ago	view ↗
scicode aa_scicode	2.31	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	4h ago	view ↗
critpt	0.00	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	4h ago	view ↗
HLE aa_hle	6.72	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	4h ago	view ↗
mt_bench MT-Bench	3.90	—	huggingface.colfm25-dspark	VENDOR	OTHER	12d ago	view ↗
GSM8K	4.34	—	huggingface.colfm25-dspark	VENDOR	OTHER	12d ago	view ↗
MBPP	5.52	—	huggingface.colfm25-dspark	VENDOR	OTHER	12d ago	view ↗
humaneval HumanEval	5.31	—	huggingface.colfm25-dspark	VENDOR	OTHER	12d ago	view ↗
MATH500 (Pass@1) MATH500	6.02	—	huggingface.colfm25-dspark	VENDOR	OTHER	12d ago	view ↗
math_500_em MATH-500	5.78	—	huggingface.coREADME	VENDOR	VENDOR	12d ago	view ↗
BFCL v3 BFCLv3	49.12	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
AIME25 no tools AIME25	14.00	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
ifeval IFEval	86.23	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
MMLU-Pro	44.35	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
Domain Avg	39.68	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
J-BFCLv3	46.29	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
JHumanEval+	28.66	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
J-MATH500	50.00	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
J-GSM8K	50.20	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
Avg. Avg	50.10	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
JGPQA	31.72	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
JMMLU	47.61	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
JMMLU-ProX	31.42	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
AA Agentic Index	3.61	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	76d ago	view ↗
Artificial Analysis Coding Index	0.77	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	76d ago	view ↗
gdpval	0.00	no reasoning	artificialanalysis.ai	AGGREGATOR	AGGR	79d ago	view ↗
math_500_em MATH-500	63.20	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
IFBench	47.33	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
GPQA Diamond	38.89	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
BFCL v3 BFCLv3	49.12	—	huggingface.coREADME	VENDOR	VENDOR	23d ago	view ↗
AIME25 no tools AIME25	14.00	—	huggingface.coREADME	VENDOR	VENDOR	23d ago	view ↗
ifeval IFEval	86.23	—	huggingface.coREADME	VENDOR	VENDOR	23d ago	view ↗
MMLU-Pro	44.35	—	huggingface.coREADME	VENDOR	VENDOR	23d ago	view ↗
GSM8K	64.52	—	huggingface.coREADME	UNVERIFIED	VENDOR	23d ago	view ↗
IFBench	47.33	—	huggingface.coREADME	VENDOR	VENDOR	23d ago	view ↗
GPQA Diamond GPQA	38.89	—	huggingface.coREADME	VENDOR	VENDOR	23d ago	view ↗

Comparisons — LFM2.5-1.2B-InstructTRACKED HEAD-TO-HEAD

VSGemma 3 1B Instruct· GOOGLE35SHARED BENCHMARKS VSGranite 4.0 1B· IBM34SHARED BENCHMARKS VSLlama 3.2 Instruct 1B· META33SHARED BENCHMARKS VSLFM2.5-8B-A1B· LIQUID AI24SHARED BENCHMARKS VSGPT-4o· OPENAI23SHARED BENCHMARKS VSGranite 4.0 H 1B· IBM22SHARED BENCHMARKS VSLFM2.5-1.2B-Thinking· LIQUID AI22SHARED BENCHMARKS VSLlama 3.1 Instruct 405B· META22SHARED BENCHMARKS

The Liquid AI lineLFM2.5-VL-1.6B LFM2.5-VL-3B LFM2.5-2.6B LFM2.5-8B-A1B LFM2-VL-3B LFM2-1.2B ALL LIQUID AI →