Head-to-head comparison across 1benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
LFM2.5-230M
17
LFM2.5-8B-A1B
41
Pick LFM2.5-8B-A1B if you want the stronger benchmark profile. LFM2.5-230M only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
Inst. Following
+7.8 difference
LFM2.5-230M
LFM2.5-8B-A1B
$0 / $0
$0 / $0
N/A
N/A
N/A
N/A
32K
128K
Pick LFM2.5-8B-A1B if you want the stronger benchmark profile. LFM2.5-230M only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
LFM2.5-8B-A1B is clearly ahead on the provisional aggregate, 41 to 17. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
LFM2.5-8B-A1B's sharpest advantage is in instruction following, where it averages 79.5 against 71.7. The single biggest benchmark swing on the page is IFEval, 71.7% to 91.8%.
LFM2.5-8B-A1B is the reasoning model in the pair, while LFM2.5-230M is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. LFM2.5-8B-A1B gives you the larger context window at 128K, compared with 32K for LFM2.5-230M.
LFM2.5-8B-A1B is ahead on BenchLM's provisional leaderboard, 41 to 17. The biggest single separator in this matchup is IFEval, where the scores are 71.7% and 91.8%.
LFM2.5-8B-A1B has the edge for instruction following in this comparison, averaging 79.5 versus 71.7. Inside this category, IFEval is the benchmark that creates the most daylight between them.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.