dots3-note Preview vs LFM2.5-24B-A2B
Change modelsdots3-note PreviewDots Studio
LFM2.5-24B-A2BLiquidAI
IndexAll categories, out of 100.
63.4 ±3.9 best
39.8 ±7.9
GapIndex points below the top.
Top
−23.6
CoverageIndex weight that has results.
95% best
70%
SpeedOutput tokens per second.
—
280/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-08
2026-10
Input / 1MUS dollars per 1M input tokens.
Free best
$0.05
Output / 1MUS dollars per 1M output tokens.
Free best
$0.70
1K chats2K tokens in, 500 out, each.
Free best
$0.45
1K documents20K tokens in, 1K out, each.
Free best
$1.70
1K agent tasks200K tokens in, 20K out, each.
Free best
$24.00
ContextMaximum tokens in one request.
512K best
128K
AgenticMulti-step tasks with tools.
63.3 best
32.0
CodingCode writing and repair.
60.3 best
38.7
ReasoningLogic problems and puzzles.
74.5
—
MultimodalTasks with images and text.
59.2
—
KnowledgeFacts and expert knowledge.
77.2 best
38.6
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
58.2
58.4 best
MathMath problems.
62.3 best
45.6
Benchmarks
4 sharedOnly dots3-note Preview: 23Only LFM2.5-24B-A2B: 9
dots3-note Preview
LFM2.5-24B-A2B