Back
FR

Sarvam

Sarvam 30B (High)

Models.dev
Intelligence
6.6
Rank 622 of 782 measured models
Price/1M
$0.047
Rank 58 of 740 measured models
Context window
65.5K
Rank 1020 of 1325 measured models

Sarvam 30B (High) scores 6.6 on the Artificial Analysis Intelligence Index, ranking 622nd of 782 measured models. The closest models on this index are DeepSeek-V2.5 (6.6), Gemini 2.0 Flash Thinking Experimental (Dec '24) (6.6), and Granite 4.1 8B (6.6). At $0.047 per million tokens (3:1 input/output blended price), it is cheaper than Granite 4.1 8B ($0.063).

Artificial Analysis Indices
Intelligence6.6
Rank 622 of 782 measured models
Standard Benchmarks
GPQA Diamond63.3%
Rank 384 of 621 measured models
HLE7.5%
Rank 396 of 682 measured models
IFBench26.5%
Rank 408 of 451 measured models
AA-LCR0.0%
Rank 531 of 593 measured models
TerminalBench Hard2.3%
Rank 338 of 432 measured models
τ²-Bench34.5%
Rank 252 of 440 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy