Claude 4 Sonnet vs LFM3-1.7B
Change modelsClaude 4 SonnetAnthropic
LFM3-1.7BLiquidAI
IndexAll categories, out of 100.
39.7 ±5.0
41.2 ±6.5 best
GapIndex points below the top.
−1.5 · no clear gap
Top
CoverageIndex weight that has results.
95% best
75%
SpeedOutput tokens per second.
40/s
193/s best
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2025-05
2026-10
Input / 1MUS dollars per 1M input tokens.
$3.00
$0.08 best
Output / 1MUS dollars per 1M output tokens.
$15.00
$0.20 best
1K chats2K tokens in, 500 out, each.
$13.50
$0.26 best
1K documents20K tokens in, 1K out, each.
$75.00
$1.80 best
1K agent tasks200K tokens in, 20K out, each.
$900.00
$20.00 best
ContextMaximum tokens in one request.
200K
262K best
AgenticMulti-step tasks with tools.
44.8
45.7 best
CodingCode writing and repair.
51.6 best
36.7
ReasoningLogic problems and puzzles.
38.0
43.3 best
MultimodalTasks with images and text.
36.2
—
KnowledgeFacts and expert knowledge.
36.4 best
29.7
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
31.7
56.7 best
MathMath problems.
17.0
—
Benchmarks
3 sharedOnly Claude 4 Sonnet: 14Only LFM3-1.7B: 22
Claude 4 Sonnet
LFM3-1.7B