Head-to-head comparison across 1benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
LFM2.5-8B-A1B
50
MiMo-V2-Flash
59
Pick MiMo-V2-Flash if you want the stronger benchmark profile. LFM2.5-8B-A1B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
Math
+34.2 difference
LFM2.5-8B-A1B
MiMo-V2-Flash
$0 / $0
$0 / $0
N/A
129 t/s
N/A
2.14s
128K
256K
Pick MiMo-V2-Flash if you want the stronger benchmark profile. LFM2.5-8B-A1B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
MiMo-V2-Flash is clearly ahead on the provisional aggregate, 59 to 50. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
MiMo-V2-Flash's sharpest advantage is in mathematics, where it averages 94.1 against 59.9. The single biggest benchmark swing on the page is AIME 2025, 42.5% to 94.1%.
MiMo-V2-Flash gives you the larger context window at 256K, compared with 128K for LFM2.5-8B-A1B.
MiMo-V2-Flash is ahead on BenchLM's provisional leaderboard, 59 to 50. The biggest single separator in this matchup is AIME 2025, where the scores are 42.5% and 94.1%.
MiMo-V2-Flash has the edge for math in this comparison, averaging 94.1 versus 59.9. Inside this category, AIME 2025 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.