VerdictPal
Join

Models / Liquid

LFM2.5-8B-A1B

LFM · Released 2026-06-08

Liquid's compact LFM 2.5 model evaluated by Artificial Analysis on 8 Jun. Keep it in the efficiency lane until local benchmark and pricing rows are imported.

Tiny efficiency model for routing, extraction, and on-device-adjacent experiments where footprint matters more than peak reasoning.

#165 of 168 on AA Index · current snapshot
8 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite20
Context128K
Input / 1M—
Output / 1M—
Knowledge cutoffopen
Output speed346 t/s
TTFT (default API)1.54s
Statuslightweight

Family profile

Best published score in each covered benchmark family.

17/100 avg
Reasoning
56
Coding
8
Agentic
5
Long context
0

4 tested benchmark families

Benchmark placements

Where LFM2.5-8B-A1B places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
AA output speedPerformance#3/ 187Artificial Analysis2026-09-01
AA time to first tokenPerformance#43/ 186Artificial Analysis2026-09-01
IFBenchReasoning#90/ 12756Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#164/ 1807Artificial Analysis2026-09-01
SciCodeCoding#176/ 1808Artificial Analysis2026-09-01
GPQA DiamondReasoning#178/ 18551Artificial Analysis2026-09-01
AA-LCRLong context#179/ 1790Artificial Analysis2026-09-01
Terminal-BenchAgentic#180/ 1845Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#184/ 1878Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where LFM2.5-8B-A1B shows up, it's highlighted.

ReasoningLFM2.5-8B-A1B · 56
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
CodingLFM2.5-8B-A1B · 8
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticLFM2.5-8B-A1B · 5
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Newest receipts

Benchmark rows added to the public ledger for LFM2.5-8B-A1B in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context0%Artificial Analysis5
AA output speedPerformance346 t/sArtificial Analysis5
AA time to first tokenPerformance1.54sArtificial Analysis5
Artificial Analysis Intelligence IndexReasoning8.1%Artificial Analysis5
GPQA DiamondReasoning51.3%Artificial Analysis5
Humanity's Last ExamReasoning6.9%Artificial Analysis5
IFBenchReasoning55.65%Artificial Analysis5
SciCodeCoding7.8%Artificial Analysis5
Terminal-BenchAgentic4.55%Artificial Analysis5
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning56
Coding8
Agentic5
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for LFM2.5-8B-A1B. Scores link to the original source; gaps mean no public row exists yet.

9 sourced rows

9 of 37 catalog benchmarks have a sourced row for LFM2.5-8B-A1B.

Reasoning

Coding

Agentic

Long context

Performance

Sources