LFM2-VL-3B
LFM2-VL-3B is behind the leaders in multimodal tasks. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multilingual tasks, instruction following, or factuality.
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, Multilingual, Instruction Following or Factuality.
Price
No current price is tracked for this model. See the rate card
Evidence
48results on33benchmarks
- 35 vendor-reported
- 13 cross-referenced
From 3 sources · latest Sep 10, 2026 · How verification works
LFM2-VL-3B benchmark results
48 results on 33 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
52.0% behind the leader3 of 6 ranked benchmarks measured
- 822.00Aug 9, 2026
- MathVista62.10Aug 22, 2026MathVista (mini)
- 28.70Aug 22, 2026
0 of 3 ranked benchmarks measured
- 20.80Sep 10, 2026
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- 20.50Sep 10, 2026
- 72.90Sep 10, 2026
- 2.50Sep 10, 2026
- 7.60Sep 10, 2026
- 6.00Sep 10, 2026
- 89.20Sep 10, 2026
Show 29 more resultsHide 29 results
- 20.50Aug 12, 2026
- 80.40Aug 12, 2026
- ChartQA Test80.40Sep 10, 2026ChartQA (test)
- DocVQA-val89.80Aug 22, 2026DocVQA (val)
- 46.40Sep 10, 2026
- 67.80Aug 22, 2026
- 51.40Aug 22, 2026
- 51.83Aug 9, 2026
- 51.40Aug 12, 2026
- MMBench80.00Sep 10, 2026MMBench (dev EN v1.1)
- 79.81Aug 9, 2026
- 73.00Aug 22, 2026
- 73.00Aug 12, 2026
- 81.90Aug 22, 2026
- 81.90Aug 12, 2026
- MMMU (val) (Pass@1)45.60Aug 22, 2026MMMU (val)
- 76.30Aug 22, 2026
- 81.90Sep 10, 2026
- 81.70Aug 22, 2026
- OCRBench v2_en43.90Sep 10, 2026OCRBench v2 (En)
- 89.01Aug 9, 2026
- 89.20Aug 12, 2026
- 71.10Aug 22, 2026
- 71.37Aug 9, 2026
- 71.10Aug 12, 2026
- 57.10Aug 12, 2026
- 76.60Aug 22, 2026
- 33.00Aug 22, 2026
- TextVQA-val83.00Sep 10, 2026TextVQA (val)
LFM2-VL-3B: common questions
Who makes LFM2-VL-3B?
LFM2-VL-3B is made by Liquid AI.
When was LFM2-VL-3B released?
LFM2-VL-3B's weights were first published on Hugging Face on Oct 22, 2025.
What is LFM2-VL-3B good at?
LFM2-VL-3B is behind the leaders in multimodal tasks. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multilingual tasks, instruction following, or factuality.
How many benchmarks has LFM2-VL-3B been tested on?
We track 48 results for LFM2-VL-3B on 33 benchmarks from 3 sources. The latest was recorded on Sep 10, 2026.
About this record
Where LFM2-VL-3B's numbers come from, and every name it appears under.
- Tracked since
- Aug 9, 2026
- Newest source mention
- Aug 9, 2026
Where the results come from
Verification: 48 scores · 0 independently verified · 13 vendor cross-reference · 35 vendor-reported. How these tiers are assigned
From 3 sources on 1 site. Hugging Face supplies all of them. Bars are coloured by trust tier.
- huggingface.co48