LFM2.5-8B-A1B vs Sarvam 30B
Change modelsLFM2.5-8B-A1BLiquidAI
Sarvam 30BSarvam
IndexAll categories, out of 100.
30.6 ±7.5 best
30.3 ±5.8
GapIndex points below the top.
Top
−0.3 · no clear gap
CoverageIndex weight that has results.
70%
85% best
SpeedOutput tokens per second.
335/s
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-05
2026-03
Input / 1MUS dollars per 1M input tokens.
—
—
Output / 1MUS dollars per 1M output tokens.
—
—
1K chats2K tokens in, 500 out, each.
—
—
1K documents20K tokens in, 1K out, each.
—
—
1K agent tasks200K tokens in, 20K out, each.
—
—
ContextMaximum tokens in one request.
128K best
64K
AgenticMulti-step tasks with tools.
46.3 best
26.8
CodingCode writing and repair.
—
29.4
ReasoningLogic problems and puzzles.
22.1
22.4 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
26.0
36.8 best
MultilingualTasks in many languages.
5.0
—
InstructionTasks with strict prompt rules.
44.8 best
13.8
MathMath problems.
27.1
37.9 best
Benchmarks
7 sharedOnly LFM2.5-8B-A1B: 14Only Sarvam 30B: 8
LFM2.5-8B-A1B
Sarvam 30B