← All comparisons

Claude 3.5 Sonnet (Oct '24) vs Sarvam M (Reasoning)

Anthropic vs Sarvam — side-by-side benchmark comparison

Claude 3.5 Sonnet (Oct '24)Sarvam M (Reasoning)
Intelligence Index15.98.4
Coding Index30.27.5
Math Index
Output speed (tok/s)0.0142.2
Blended price ($/1M)$6.56$0.00
Time to first token (s)0.00s1.16s
aime15.7%20.3%
aime 25
artificial analysis coding index30.207.50
artificial analysis intelligence index15.908.40
artificial analysis math index
gpqa59.9%41.6%
hle3.9%3.3%
ifbench31.8%
lcr0.0%
livecodebench38.1%29.5%
math 50077.1%84.7%
mmlu pro77.2%69.6%
scicode36.6%17.8%
tau20.0%
terminalbench hard2.3%

Benchmark data from Artificial Analysis.