Ling 2.6 Flash vs Sarvam 105B
Change modelsLing 2.6 FlashInclusionAI
Sarvam 105BSarvam
IndexAll categories, out of 100.
37.0 ±7.9 best
36.7 ±5.7
GapIndex points below the top.
Top
−0.3 · no clear gap
CoverageIndex weight that has results.
75%
85% best
SpeedOutput tokens per second.
104/s
191/s best
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-04
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.
262K best
128K
AgenticMulti-step tasks with tools.
46.9 best
36.4
CodingCode writing and repair.
31.0
34.4 best
ReasoningLogic problems and puzzles.
32.8 best
22.1
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
30.8
42.4 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
42.5 best
27.6
MathMath problems.
—
46.6
Benchmarks
6 sharedOnly Ling 2.6 Flash: 5Only Sarvam 105B: 10
Ling 2.6 Flash
Sarvam 105B