Head-to-head comparison across 2benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
LFM2.5-VL-450M
0
ZAYA1-8B
62
Pick ZAYA1-8B 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.
Knowledge
+51.5 difference
Inst. Following
+12.8 difference
LFM2.5-VL-450M
ZAYA1-8B
$0 / $0
$0 / $0
N/A
N/A
N/A
N/A
128K
131K
Pick ZAYA1-8B 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.
ZAYA1-8B is clearly ahead on the provisional aggregate, 62 to 0. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
ZAYA1-8B's sharpest advantage is in knowledge, where it averages 73.1 against 21.6. The single biggest benchmark swing on the page is MMLU-Pro, 19.3% to 74.2%.
ZAYA1-8B 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. ZAYA1-8B gives you the larger context window at 131K, compared with 128K for LFM2.5-VL-450M.
ZAYA1-8B is ahead on BenchLM's provisional leaderboard, 62 to 0. The biggest single separator in this matchup is MMLU-Pro, where the scores are 19.3% and 74.2%.
ZAYA1-8B has the edge for knowledge tasks in this comparison, averaging 73.1 versus 21.6. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
ZAYA1-8B has the edge for instruction following in this comparison, averaging 74 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.