LFM2.5-24B-A2B vs LFM3-1.7B
Change modelsLFM2.5-24B-A2BLiquidAI
LFM3-1.7BLiquidAI
IndexAll categories, out of 100.
39.8 ±7.9
41.5 ±6.5 best
GapIndex points below the top.
−1.7 · no clear gap
Top
CoverageIndex weight that has results.
70%
75% best
SpeedOutput tokens per second.
280/s best
218/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-10
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.05 best
$0.08
Output / 1MUS dollars per 1M output tokens.
$0.70
$0.20 best
1K chats2K tokens in, 500 out, each.
$0.45
$0.26 best
1K documents20K tokens in, 1K out, each.
$1.70 best
$1.80
1K agent tasks200K tokens in, 20K out, each.
$24.00
$20.00 best
ContextMaximum tokens in one request.
128K
262K best
AgenticMulti-step tasks with tools.
32.0
46.4 best
CodingCode writing and repair.
38.7 best
37.0
ReasoningLogic problems and puzzles.
—
43.5
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
38.6 best
28.8
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
58.4 best
57.6
MathMath problems.
45.6
—
Benchmarks
11 sharedOnly LFM2.5-24B-A2B: 2Only LFM3-1.7B: 14
LFM2.5-24B-A2B
LFM3-1.7B