DeepSeek V3 vs Sarvam 30B
Change modelsDeepSeek V3DeepSeek
Sarvam 30BSarvam
IndexAll categories, out of 100.
29.9 ±4.9
30.3 ±5.8 best
GapIndex points below the top.
−0.4 · no clear gap
Top
CoverageIndex weight that has results.
85%
85%
SpeedOutput tokens per second.
37/s
—
EloLMArena rating and rank.
1333
—
ReleasedMonth of release.
2024-12
2026-03
Input / 1MUS dollars per 1M input tokens.
$0.27
—
Output / 1MUS dollars per 1M output tokens.
$1.10
—
1K chats2K tokens in, 500 out, each.
$1.09
—
1K documents20K tokens in, 1K out, each.
$6.50
—
1K agent tasks200K tokens in, 20K out, each.
$76.00
—
ContextMaximum tokens in one request.
128K best
64K
AgenticMulti-step tasks with tools.
26.0
26.8 best
CodingCode writing and repair.
31.1 best
29.4
ReasoningLogic problems and puzzles.
34.1 best
22.4
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
34.3
36.8 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
29.1 best
13.8
MathMath problems.
27.2
37.9 best
Benchmarks
9 sharedOnly DeepSeek V3: 25Only Sarvam 30B: 6
DeepSeek V3
Sarvam 30B