Benchmark Almanac

LFM2-1.2B

LFM2-1.2B.

Liquid AI Released 10 Jul 2025 Family LFM2 The lab's model card
12
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Liquid AI Jul 2025

LFM2-1.2B

Open weights Small

No Epoch Capabilities Index score yet
  • IFBench 20.7% #70 /70
  • MMLU-Pro 19.7% #150 /151
  • IFEval 74.9% #110 /126

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
IFEval 74.9% #110 of 126 Model card
MGSM 55% #47 of 52 Model card
MMLU 55.2% #118 of 127 Model card
Multi-IF 45.3% #27 of 28 Model card
MMMLU 46.7% #60 of 62 Model card
MMLU-Pro 19.7% #150 of 151 Model card
IFBench 20.7% #70 of 70 Model card

Math and science

BenchmarkScoreRankSource
GSM8K 58.3% #78 of 87 Model card
GPQA Diamond 31.5% #274 of 284 Model card
MATH-500 42.4% #65 of 67 Model card
GSM-Plus 36.1% #2 of 2 Model card
MATH Level 5 18.6% #2 of 2 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. 5 of them aren't in the launch post.