Skip to main content

Compare Leaderboards Agents Insights

Loading...

Compare LLM models by quality, speed, and price. Find the right model for your use case.

Product

Explore Models
Compare
Leaderboards
LLM Selector
Cost Calculator
Provider Finder

Resources

Insights
FAQ
About
Methodology

Data Sources

Data from Artificial Analysis, OpenRouter, HuggingFace, and other public sources.

© 2026 FindLLM. All rights reserved.

Sarvam 30B (high) — Sarvam | FindLLM

Home
Explore
Sarvam 30B (high)

Back to Explore

Sarvam 30B (high)

Sarvam·Released 2026-03-06

Related Models

Sarvam 105B (high)2026-03-06 Sarvam M (Reasoning)2025-05-23

Performance

169

tokens/sec

Faster than 84% of models

1.21

seconds

Faster than 42% of models

13.07

seconds

Faster than 36% of models

Market Median

86 tok/s

96% faster

Median TTFT

1.07s

13% slower

Speed Comparison

LongCat Flash Lite

169 tok/s+0%

GPT-5 (ChatGPT)

168 tok/s-0%

OpenAI: GPT-5 Codex

169 tok/s+0%

Benchmarks

MMLU-ProNot evaluated

GPQA Diamond

63.3%

HLE

7.0%

LiveCodeBenchNot evaluated

SciCode

19.2%

TerminalBench Hard

2.3%

MATH-500Not evaluated

AIMENot evaluated

AIME 2025Not evaluated

IFBench

26.5%

Long Context Recall

0.0%

Tau2

34.5%

Market AverageTop Score

Quick Compare

Similar Models

Anthropic: Claude 3 Haiku

Anthropic

Q: 12.3$0.50/1M200K ctx

Gemini 2.0 Flash Thinking Experimental (Dec '24)

Google

DeepSeek-V2.5

DeepSeek

IBM: Granite 4.1 8B

IBM

Q: 12.4$0.06/1M131K ctx

Olmo 3.1 32B Instruct

Allen AI

Q: 12.2$0.30/1M66K ctx

Llama 3.1 Instruct 70B

Meta

Q: 12.5$0.56/1M

Compare all 7 models

Quality Index

12.3

385th of 507

Top 77%

Coding Index

7.9

344th of 417

Top 82%

Speed

169 tok/s

Top 16%

TTFT

1.21s

Market Position

Sarvam 30B (high)Market Average