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 105B (high) — Sarvam | FindLLM

Home
Explore
Sarvam 105B (high)

Back to Explore

Sarvam 105B (high)

Sarvam·Released 2026-03-06

Related Models

Sarvam 30B (high)2026-03-06 Sarvam M (Reasoning)2025-05-23

Performance

107

tokens/sec

Faster than 61% of models

1.26

seconds

Faster than 39% of models

19.89

seconds

Faster than 26% of models

Market Median

86 tok/s

25% faster

Median TTFT

1.07s

18% slower

Speed Comparison

MiMo-V2-Omni-0327

107 tok/s-0%

Qwen3 Omni 30B A3B Instruct

109 tok/s+1%

Qwen3 4B (Non-reasoning)

106 tok/s-1%

Benchmarks

MMLU-ProNot evaluated

GPQA Diamond

73.8%

HLE

10.1%

LiveCodeBenchNot evaluated

SciCode

26.4%

TerminalBench Hard

1.5%

MATH-500Not evaluated

AIMENot evaluated

AIME 2025Not evaluated

IFBench

34.4%

Long Context Recall

0.0%

Tau2

46.8%

Market AverageTop Score

Quick Compare

Similar Models

Magistral Small 1.2

Mistral

Q: 18.2$0.75/1M

Qwen3 4B 2507 (Reasoning)

Alibaba

Gemini 2.0 Pro Experimental (Feb '25)

Google

Meta: Llama 4 Maverick

Meta

Q: 18.4$0.26/1M1.0M ctx

Nova 2.0 Lite (Non-reasoning)

Amazon

Q: 18.0$0.85/1M

Claude 3 Opus

Anthropic

Q: 18.0$32.81/1M

Compare all 7 models

Quality Index

18.2

272nd of 507

Top 54%

Coding Index

9.8

326th of 417

Top 79%

Speed

107 tok/s

Top 39%

TTFT

1.26s

Market Position

Sarvam 105B (high)Market Average