Kimi K2 vs LFM2.5-24B-A2B
Change modelsKimi K2Moonshot AI
LFM2.5-24B-A2BLiquidAI
IndexAll categories, out of 100.
39.6 ±5.4
39.8 ±7.9 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
85% best
70%
SpeedOutput tokens per second.
37/s
280/s best
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2025-07
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.57
$0.05 best
Output / 1MUS dollars per 1M output tokens.
$2.30
$0.70 best
1K chats2K tokens in, 500 out, each.
$2.29
$0.45 best
1K documents20K tokens in, 1K out, each.
$13.70
$1.70 best
1K agent tasks200K tokens in, 20K out, each.
$160.00
$24.00 best
ContextMaximum tokens in one request.
131K best
128K
AgenticMulti-step tasks with tools.
44.9 best
32.0
CodingCode writing and repair.
39.0 best
38.7
ReasoningLogic problems and puzzles.
40.3
—
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
41.5 best
38.6
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
35.9
58.4 best
MathMath problems.
36.0
45.6 best
Benchmarks
5 sharedOnly Kimi K2: 20Only LFM2.5-24B-A2B: 8
Kimi K2
LFM2.5-24B-A2B