Back

Sarvam

Sarvam 105B (High)

ReasoningOpen weightsModels.dev
Intelligence
8.8
Rank 479 of 748 measured models
Output speed
224 t/s
Rank 30 of 408 measured models
Price/1M
$0.074
Rank 70 of 667 measured models
Context window
128K
Rank 780 of 1211 measured models

Sarvam 105B (High) scores 8.8 on the Artificial Analysis Intelligence Index, ranking 479th of 748 measured models. The closest models on this index are Claude 3.5 Haiku (8.9), MiniCPM5-1B (8.8), and Qwen3 4B 2507 (Reasoning) (8.8).

Artificial Analysis Indices
Intelligence8.8
Rank 479 of 748 measured models
Standard Benchmarks
GPQA Diamond73.8%
Rank 283 of 620 measured models
HLE11.0%
Rank 317 of 668 measured models
IFBench34.4%
Rank 337 of 450 measured models
AA-LCR0.0%
Rank 517 of 579 measured models
TerminalBench Hard1.5%
Rank 358 of 432 measured models
τ²-Bench46.8%
Rank 217 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