QwQ-32B vs Sarvam 105B
Change modelsQwQ-32BAlibaba
Sarvam 105BSarvam
IndexAll categories, out of 100.
36.3 ±9.5
36.7 ±5.7 best
GapIndex points below the top.
−0.4 · no clear gap
Top
CoverageIndex weight that has results.
50%
85% best
SpeedOutput tokens per second.
—
191/s
EloLMArena rating and rank.
1329
—
ReleasedMonth of release.
2025-03
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.
131K best
128K
AgenticMulti-step tasks with tools.
—
36.4
CodingCode writing and repair.
—
34.4
ReasoningLogic problems and puzzles.
25.6 best
22.1
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
38.4
42.4 best
MultilingualTasks in many languages.
33.0
—
InstructionTasks with strict prompt rules.
28.7 best
27.6
MathMath problems.
41.9
46.6 best
Benchmarks
7 sharedOnly QwQ-32B: 10Only Sarvam 105B: 9
QwQ-32B
Sarvam 105B