Benchmark Almanac

LFM2-VL-1.6B

LFM2-VL-1.6B.

Liquid AI Released 12 Aug 2025 Family LFM2 The lab's model card
14
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Liquid AI Aug 2025

LFM2-VL-1.6B

Open weights Small

No Epoch Capabilities Index score yet
  • BLINK 44.5% #25 /28
  • MM-Vet 48.1% #8 /8
  • MathVista 51.7% #59 /64

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
POPE 87.2% #4 of 7 Model card
MMLU 51% #121 of 127 Model card
MM-IFEval 46.4% #3 of 3 Model card

Vision, audio and robotics

BenchmarkScoreRankSource
MME 1757.0 #5 of 6 Model card
RealWorldQA 65.8% #26 of 30 Model card
BLINK 44.5% #25 of 28 Model card
MathVista 51.7% #59 of 64 Model card
InfographicVQA 58.7% #21 of 22 Model card
MMMU 39.7% #96 of 97 Model card
MMStar 49.9% #30 of 30 Model card
OCRBench 74.2% #28 of 28 Model card
MMBench 69.2% #9 of 9 Model card
MM-Vet 48.1% #8 of 8 Model card
SEED-Bench 72% #3 of 3 Model card

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Its system card

Every result in the longer documents the lab published with it. 2 of them aren't in the launch post.