LFM2.5-24B-A2B vs LongCat-Flash-Lite-Sparse

Change models
LFM2.5-24B-A2BLiquidAI
IndexAll categories, out of 100.
39.4 ±7.9 best
39.1 ±7.8
GapIndex points below the top.
Top
−0.3 · no clear gap
CoverageIndex weight that has results.
70% best
65%
SpeedOutput tokens per second.
405/s
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-10
2026-07
Input / 1MUS dollars per 1M input tokens.
$0.05
—
Output / 1MUS dollars per 1M output tokens.
$0.70
—
1K chats2K tokens in, 500 out, each.
$0.45
—
1K documents20K tokens in, 1K out, each.
$1.70
—
1K agent tasks200K tokens in, 20K out, each.
$24.00
—
ContextMaximum tokens in one request.
128K
1M best
AgenticMulti-step tasks with tools.
31.8
39.2 best
CodingCode writing and repair.
38.6
47.2 best
ReasoningLogic problems and puzzles.
—
—
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
38.5
39.5 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
57.5
—
MathMath problems.
45.0 best
32.8

Benchmarks

3 shared
Only LFM2.5-24B-A2B: 10Only LongCat-Flash-Lite-Sparse: 12
LFM2.5-24B-A2B
LongCat-Flash-Lite-Sparse
51.0%95 / 114
68.2% best77 / 114
74.4% best72 / 87
69.5%76 / 87
96.0% best14 / 29
95.8%16 / 29