Back

Amazon

Nova Premier

Closed weightsModels.dev
Intelligence
9.2
Rank 453 of 744 measured models
Price/1M
$5
Rank 579 of 659 measured models
Context window
1M
Rank 84 of 1199 measured models

Nova Premier scores 9.2 on the Artificial Analysis Intelligence Index, ranking 453rd of 744 measured models. The closest models on this index are Ling-1T (9.2), Mistral Medium 3.1 (9.2), and Motif-2-12.7B-Reasoning (9.2). At $5 per million tokens (3:1 input/output blended price), it is more expensive than Mistral Medium 3.1 ($0.80).

Artificial Analysis Indices
Intelligence9.2
Rank 453 of 744 measured models
Math17.3
Rank 217 of 270 measured models
Standard Benchmarks
MMLU Pro73.3%
Rank 198 of 349 measured models
GPQA Diamond56.9%
Rank 430 of 619 measured models
HLE4.2%
Rank 553 of 664 measured models
LiveCodeBench31.7%
Rank 213 of 343 measured models
MATH-50083.9%
Rank 100 of 202 measured models
AIME 202417.0%
Rank 108 of 194 measured models
AIME 202517.3%
Rank 217 of 270 measured models
IFBench36.2%
Rank 322 of 450 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