Sarvam M (Reasoning)

Sarvam·Released 2025-05-23

Compare

Quality Index

8.4

460th of 507

Top 92%

Coding Index

7.5

350th of 417

Top 84%

Speed

141 tok/s

Top 26%

TTFT

1.17s

Market Position

Sarvam M (Reasoning)Market Average

Performance

141

tokens/sec

Faster than 74% of models

1.17

seconds

Faster than 43% of models

15.37

seconds

Faster than 31% of models

Market Median

86 tok/s

64% faster

Median TTFT

1.07s

9% slower

Speed Comparison

Qwen3 1.7B (Non-reasoning)

141 tok/s+0%

Qwen3.5 9B (Non-reasoning)

141 tok/s+0%

LFM2 24B A2B

142 tok/s+1%

Benchmarks

MMLU-Pro

69.6%

GPQA Diamond

41.6%

HLE

3.3%

LiveCodeBench

29.5%

SciCode

17.8%

TerminalBench Hard

2.3%

MATH-500

84.7%

AIME

20.3%

AIME 2025Not evaluated

IFBench

31.8%

Long Context Recall

0.0%

Tau2

0.0%

Market AverageTop Score

Quick Compare

Similar Models

Microsoft: Phi 4 Mini Instruct

Microsoft

Q: 8.4$0.15/1M128K ctx

Slower: 68%Coding: -3.9

Llama 2 Chat 13B

Market Position

Sarvam M (Reasoning)Market Average

Sarvam M (Reasoning)

Related Models

Market Position

Performance

Benchmarks

Quick Compare

Similar Models

Market Position