S
Sarvam 105B (high)
Last updated: Recently
Model Type
Text
Max Context
-
Max Output
-
Parameter Scale
-
Sarvam 105B high by Sarvam: Text model; TTFT 1.246s, 152.7 tok/s.
Input Modality
-
Output Modality
-
Inference Speed
152.749 tokens/s
Latest Release Date
3/6/2026
SDK Ecosystem
-
artificial-analysismanufactureraa-bootstrap
Model Overview Fields
name
Sarvam 105B (high)
Release date
3/6/2026
Performance
152.749 tokens/s
model_creator.name
Sarvam
AA Evaluation Scores
AA Intelligence Index
18.2
AA Coding Index
9.8
AA Math Index
-
MMLU Pro
-
GPQA
0.738
HLE
0.101
LiveCodeBench
-
SciCode
0.264
Math-500
-
AIME
-
AIME 2025
-
IFBench
0.344
LCR
0
TerminalBench Hard
0.015
TAU2
0.468
Output Speed (tokens/s)
152.749 tok/s
TTFT (s)
1.246s
First Answer Token (s)
14.339s