Sarvam 105B (high)

SarvamIndia

Sarvam 105B is a large language model with 105 billion parameters, designed for high-performance tasks. It is optimized for strong reasoning capabilities and handling long-context information.

ReasoningLong context

Input / 1M tokens

$0.042

Output / 1M tokens

$0.17

Output tokens/s

149.16

First-token seconds

1.2s

Supported plans

Benchmark history

Evaluations

TAU2

Measured Jul 10, 2026Source

Score

0.47

Terminalbench Hard

Measured Jul 10, 2026Source

Score

0.02

Lcr

Measured Jul 10, 2026Source

Score

Ifbench

Measured Jul 10, 2026Source

Score

0.34

Scicode

Measured Jul 10, 2026Source

Score

0.26

Hle

Measured Jul 10, 2026Source

Score

0.1

Gpqa

Measured Jul 10, 2026Source

Score

0.74

Artificial Analysis Intelligence Index

Measured Jul 10, 2026Source

Score

11.9

Plan availability

Products and plans that support this model

No products or plans have been linked to this model yet.

User ratings

Loading ratings...

Discussion

Thinking... Make sure you are connected to GitHub server