LFM2.5-2.6B vs LFM2.5-24B-A2B
Change modelsLFM2.5-2.6BLiquidAI
LFM2.5-24B-A2BLiquidAI
IndexAll categories, out of 100.
29.3 ±6.0
39.8 ±7.9 best
GapIndex points below the top.
−10.5
Top
CoverageIndex weight that has results.
85% best
70%
SpeedOutput tokens per second.
189/s
280/s best
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-08
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.35
$0.05 best
Output / 1MUS dollars per 1M output tokens.
$0.50 best
$0.70
1K chats2K tokens in, 500 out, each.
$0.95
$0.45 best
1K documents20K tokens in, 1K out, each.
$7.50
$1.70 best
1K agent tasks200K tokens in, 20K out, each.
$80.00
$24.00 best
ContextMaximum tokens in one request.
128K
128K
AgenticMulti-step tasks with tools.
32.0
32.0
CodingCode writing and repair.
23.9
38.7 best
ReasoningLogic problems and puzzles.
24.0
—
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
29.5
38.6 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
44.3
58.4 best
MathMath problems.
27.2
45.6 best
Benchmarks
4 sharedOnly LFM2.5-2.6B: 9Only LFM2.5-24B-A2B: 9
LFM2.5-2.6B
LFM2.5-24B-A2B