TAU2
Measured Jul 10, 2026Source
Score
0.35
Models8 0 
Sarvam 30B (high)
SarvamSarvamIndia
Sarvam 30B (high) is a 30-billion parameter language model developed by the Indian AI company Sarvam. It is optimized for multilingual understanding and generation, with a particular focus on Indian languages, aiming to provide high-quality performance for diverse linguistic tasks.
ReasoningMultimodal
Input / 1M tokens
$0.026Output / 1M tokens
$0.11Output tokens/s
230.6First-token seconds
1.16sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured Jul 10, 2026Source
Score
0.02
Lcr
Measured Jul 10, 2026Source
Score
0
Ifbench
Measured Jul 10, 2026Source
Score
0.26
Scicode
Measured Jul 10, 2026Source
Score
0.19
Hle
Measured Jul 10, 2026Source
Score
0.07
Gpqa
Measured Jul 10, 2026Source
Score
0.63
Artificial Analysis Intelligence Index
Measured Jul 10, 2026Source
Score
6.6
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