LFM2.5-8B-A1B
LFM2.5-8B-A1B is behind the leaders in instruction following and factuality. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multimodal tasks, or multilingual tasks.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Reasoning, Coding, Agentic, Safety, Long Context, Math, Multimodal or Multilingual.
Price
No current price is tracked for this model. See the rate card
Evidence
29results on27benchmarks
- 15 aggregator
- 14 vendor-reported
From 3 sources · latest Oct 8, 2026 · How verification works
LFM2.5-8B-A1B benchmark results
29 results on 27 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
36.1% behind the leader1 of 3 ranked benchmarks measured
- IFBench55.65Oct 8, 2026aa_ifbench
Show 1 more instruction following resultHide 1 instruction following result
- 56.47Aug 9, 2026
39.6% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Non-hallucination53.09Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy9.33Oct 8, 2026omniscienceAccuracy
0 of 6 ranked benchmarks measured
- 0.00Oct 8, 2026
- GPQA Diamond51.31Oct 8, 2026gpqa
- Humanity's Last Exam6.86Oct 8, 2026aa_hle
0 of 10 ranked benchmarks measured
- Terminal-Bench Hard4.55Oct 8, 2026aa_terminalbench_hard
- SciCode7.75Sep 4, 2026aa_scicode
0 of 7 ranked benchmarks measured
- 0.00Jun 15, 2026
0 of 3 ranked benchmarks measured
- 0.00Oct 8, 2026
0 of 5 ranked benchmarks measured
- AIME 202650.00Aug 9, 2026AIME26
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- τ²-Bench Telecom (AA run)16.08Oct 8, 2026aa_tau2
- AA Intelligence7.22Oct 8, 2026aa_intelligence_index
- -33.20Oct 8, 2026
- 5.62Jun 18, 2026
- 5.36Jun 18, 2026
- 8.52Aug 30, 2026
Show 11 more resultsHide 11 results
- AIME25 no tools42.53Aug 9, 2026AIME25
- 64.79Aug 9, 2026
- 49.73Aug 9, 2026
- 4.02Aug 30, 2026
- 7.02Aug 30, 2026
- 91.84Aug 9, 2026
- MATH500 (Pass@1)8.27Aug 30, 2026MATH500
- MATH500 (Pass@1)88.76Aug 9, 2026MATH500
- 6.93Aug 30, 2026
- 88.07Aug 9, 2026
- τ²-Bench (Retail)39.82Aug 9, 2026Tau² Retail
LFM2.5-8B-A1B: common questions
Who makes LFM2.5-8B-A1B?
LFM2.5-8B-A1B is made by Liquid AI.
When was LFM2.5-8B-A1B released?
LFM2.5-8B-A1B was released on May 28, 2026, according to Artificial Analysis.
What is LFM2.5-8B-A1B good at?
LFM2.5-8B-A1B is behind the leaders in instruction following and factuality. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multimodal tasks, or multilingual tasks.
How many benchmarks has LFM2.5-8B-A1B been tested on?
We track 29 results for LFM2.5-8B-A1B on 27 benchmarks from 3 sources. The latest was recorded on Oct 8, 2026.
About this record
Where LFM2.5-8B-A1B's numbers come from, and every name it appears under.
- Tracked since
- Jun 22, 2026
- Newest source mention
- Jun 22, 2026
Where the results come from
Verification: 29 scores · 0 independently verified · 15 aggregator-attributed · 14 vendor-reported. How these tiers are assigned
From 3 sources on 2 sites. Artificial Analysis supplies 15 of them. Bars are coloured by trust tier.
- artificialanalysis.ai15
- huggingface.co14