Skip to main content
ModelScale

LFM2.5-8B-A1B

LiquidAI · Open Weight · rank 176 · bench-align-v5

Self-hosted
Compare this model Model a workload
Canonical idlfm2-5-8b-a1b
Overall score39.15
Context window128K tokens
Release date2026-05-28
Access typeOpen Weight
Blended $/1MUnavailable75% input / 25% output

Capability shape

Seven axes from the ranking source. A missing axis is drawn as a gap.

Capability evidence

AgenticUnavailable
CodingUnavailable
Knowledge33.9
Reasoning21
Multimodal & GroundedUnavailable
Instruction Following44.7
Math27.7

Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.

Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.

Evidence key: Observed

Runtime measurements
MeasurementValueObservedLast goodEvidence
Time to first token7.62 s2026-09-172026-09-17
Throughput335 tok/s2026-09-172026-09-17

Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.

Endpoint and price matrix

Every published price component, including cache reads and writes.

Price components
ComponentUSDEvidence
Input / 1M tokensUnavailable
Output / 1M tokensUnavailable
Cache read / 1M tokensUnavailable
Cache write / 1M tokensUnavailable
Blended / 1M (75% input / 25% output)Unavailable
Self-hosted listingLiquid AI's May 28, 2026 launch post and Hugging Face model card publish open-weight LFM2.5-8B-A1B checkpoints for local/self-hosted use. Liquid does not publish a separate hosted API token price for this model, so BenchLM represents it as self-host/free-per-token.No hosted token rate was published for this model, so its per-token price is unavailable rather than zero.

Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.

Modelled monthly costUnavailableThe applicable input rate is unavailable.
Modelled tokensUnavailable
Open the simulatorChange this workload

Benchmark record

16 matched benchmark rows with their published value, unit, and provenance.

Knowledge

Knowledge benchmarks
BenchmarkValueTasksDifficultyProvenance
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index
7.2Cross-benchmark intelligence indexDisplay-only external referenceArtificial Analysis
AA-GPQA Diamond
Artificial Analysis GPQA Diamond
51.3Graduate-level science questionsGraduate-level science reasoningArtificial Analysis GPQA Diamond Benchmark Leaderboard
AA-HLE
Artificial Analysis Humanity's Last Exam
6.9Expert-level questionsFrontier expert reasoningArtificial Analysis Humanity's Last Exam Benchmark Leaderboard
AA-Omniscience Index
Artificial Analysis Omniscience Index
-33.3Knowledge questionsBroad factual knowledgeAA-Omniscience: Knowledge and Hallucination Benchmark
AA-Omniscience Accuracy
Artificial Analysis Omniscience Accuracy
9.4Knowledge questionsBroad knowledgeArtificial Analysis model benchmarks
AA-Omniscience Hallucination Rate
Artificial Analysis Omniscience Hallucination Rate
46.9Knowledge questionsFactualityArtificial Analysis model benchmarks

Mathematics

Mathematics benchmarks
BenchmarkValueTasksDifficultyProvenance
AIME 2025
American Invitational Mathematics Examination 2025
42.5315 problemsHigh school olympiad levelAmerican Invitational Mathematics Examination
MATH-500
MATH-500 Problem Set
88.76500 problemsHigh school to undergraduateMeasuring Mathematical Problem Solving With the MATH Dataset
AIME26
AIME 2026
50.0Competition math problemsOlympiad-style mathematicsQwen3.6 launch benchmarks

Reasoning

Reasoning benchmarks
BenchmarkValueTasksDifficultyProvenance
AA-LCR
Artificial Analysis Long Context Reasoning
0.0Long-context reasoning tasksLong-context reasoningArtificial Analysis model benchmarks
CritPt
Critical Physics Tasks
0.0Research-level physics questionsResearch-level physics reasoningCritPt Benchmark Leaderboard

Instruction Following

Instruction Following benchmarks
BenchmarkValueTasksDifficultyProvenance
IFEval
Instruction-Following Eval
91.84541 prompts across 25 instruction typesInstruction precisionInstruction-Following Evaluation for Large Language Models
IFBench
Instruction Following Benchmark
56.47——BenchLM
AA-IFBench
Artificial Analysis IFBench
55.6Verifiable instruction constraintsInstruction precisionArtificial Analysis IFBench Benchmark Leaderboard

Agentic

Agentic benchmarks
BenchmarkValueTasksDifficultyProvenance
τ²-bench results
τ²-Bench Tool-Agent-User Evaluation
88.07Airline, retail, and telecom customer-service task setsDual-control customer-service workflowsτ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment
BFCL v4
Berkeley Function Calling Leaderboard v4
49.7Function-calling tasksAdvanced tool useTrinity-Large-Thinking: Scaling an Open Source Frontier Agent

Lifecycle and limitations log

Lifecycle events the source associates with this model, plus what this profile does not claim.

No lifecycle event references this model.

That is not evidence the model has no lifecycle plan — only that this source published none.

What this profile does not claimValues are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned — the attempt timestamp is in each badge. Last attempted fetch for this model’s score: 2026-09-17 18:17 UTC.