Back

Anthropic

Claude 4 Sonnet

ReasoningClosed weights
Intelligence
16.6
Rank 289 of 744 measured models
Coding
37.6
Rank 164 of 298 measured models
Context window
1M
Rank 84 of 1199 measured models

Claude 4 Sonnet (Non-reasoning) scores 16.6 on the Artificial Analysis Intelligence Index, ranking 289th of 744 measured models. The closest models on this index are Claude 4 Opus (16.6), Ring-2.6-1T (16.6), and Step 3.5 Flash (16.6).

Artificial Analysis Indices
Non-reasoning
Intelligence16.6
Rank 289 of 744 measured models
Coding37.6
Rank 164 of 298 measured models
Math38.0
Rank 165 of 270 measured models
Standard Benchmarks
MMLU Pro83.7%
Rank 47 of 349 measured models
GPQA Diamond68.3%
Rank 339 of 619 measured models
HLE4.3%
Rank 540 of 664 measured models
LiveCodeBench44.9%
Rank 166 of 343 measured models
MATH-50093.4%
Rank 53 of 202 measured models
AIME 202440.7%
Rank 70 of 194 measured models
AIME 202538.0%
Rank 165 of 270 measured models
IFBench45.4%
Rank 217 of 450 measured models
Additional benchmarks7
Design Arena · 3d57.8%
Design Arena · Codecategories53.4%
Design Arena · Dataviz56.5%
Design Arena · Gamedev54.8%
Design Arena · Svg51.1%
Design Arena · Uicomponent57.9%
Design Arena · Website52.4%
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