Head-to-head comparison across 2benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
LFM2.5-230M
17
LFM2.5-VL-450M
0
Pick LFM2.5-230M if you want the stronger benchmark profile. LFM2.5-VL-450M only becomes the better choice if knowledge is the priority or you need the larger 128K context window.
Knowledge
+1.3 difference
Inst. Following
+10.5 difference
LFM2.5-230M
LFM2.5-VL-450M
$0 / $0
$0 / $0
N/A
N/A
N/A
N/A
32K
128K
Pick LFM2.5-230M if you want the stronger benchmark profile. LFM2.5-VL-450M only becomes the better choice if knowledge is the priority or you need the larger 128K context window.
LFM2.5-230M is clearly ahead on the provisional aggregate, 17 to 0. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
LFM2.5-230M's sharpest advantage is in instruction following, where it averages 71.7 against 61.2. The single biggest benchmark swing on the page is IFEval, 71.7% to 61.2%. LFM2.5-VL-450M does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
LFM2.5-VL-450M gives you the larger context window at 128K, compared with 32K for LFM2.5-230M.
LFM2.5-230M is ahead on BenchLM's provisional leaderboard, 17 to 0. The biggest single separator in this matchup is IFEval, where the scores are 71.7% and 61.2%.
LFM2.5-VL-450M has the edge for knowledge tasks in this comparison, averaging 21.6 versus 20.3. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
LFM2.5-230M has the edge for instruction following in this comparison, averaging 71.7 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.