Head-to-head comparison across 1benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
LFM2.5-8B-A1B
50
LFM2.5-VL-450M
0
Pick LFM2.5-8B-A1B if you want the stronger benchmark profile. LFM2.5-VL-450M only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
Inst. Following
+18.3 difference
LFM2.5-8B-A1B
LFM2.5-VL-450M
$0 / $0
$0 / $0
N/A
N/A
N/A
N/A
128K
128K
Pick LFM2.5-8B-A1B if you want the stronger benchmark profile. LFM2.5-VL-450M 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, 50 to 0. 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 61.2. The single biggest benchmark swing on the page is IFEval, 91.8% to 61.2%.
LFM2.5-8B-A1B is the reasoning model in the pair, while LFM2.5-VL-450M 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 is ahead on BenchLM's provisional leaderboard, 50 to 0. The biggest single separator in this matchup is IFEval, where the scores are 91.8% and 61.2%.
LFM2.5-8B-A1B has the edge for instruction following in this comparison, averaging 79.5 versus 61.2. 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.