EBEasy BenchmarksLLM model index
Workspace
Overview
Benchmarks
Benchmarks list
Overall Index
Coding
Math
MMLU-Pro
Speed
Value
Models
All models
GPT-5.5 (xhigh)
GPT-5.5 (high)
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
Gemini 3.1 Pro Preview
GPT-5.4 (xhigh)
Artificial Analysis data
Back

Sarvam

Sarvam 30B (high)

Sarvam 30B (high) is a Sarvam language-model profile in the Easy Benchmarks snapshot. Use this page to compare its measured Artificial Analysis scores, output speed, time to first token, pricing, and relative ranking against other models in the local catalog.

Sarvam model releases

Operational Metrics

Output Speed306 tok/s
First Token1.21s
Blended Price-

Model Metadata

Queryable facts extracted from the upstream model payload.

ReleaseMar 6, 2026
Context Windown/a
Modalitiesn/a
API fields: release_date

Strength: Speed

Rank #5 across 293 models.

306 tok/s

Watch Area: Coding

Rank #337 across 410 models.

7.9

Watch Area: SciCode

Rank #366 across 472 models.

19.2%

Watch Area: Overall

Rank #381 across 500 models.

12.3

Strength Profile

Percentile score by analysis domain.

Benchmark Percentiles

Higher bars mean stronger relative placement.

All Benchmarks

MetricDomainValueRank
Artificial Analysis Intelligence Indexoverall12.3#381
Artificial Analysis Coding Indexcoding7.9#337
GPQAreasoning63.3%#254
Humanity's Last Examreasoning7.0%#212
SciCode
coding, reasoning
19.2%
#366
Output Speedspeed306 tok/s#5
Time to First Tokenspeed1.21s#172