Back

Anthropic

Claude 4 Sonnet

ReasoningClosed weights
Intelligence
18.9
Rank 260 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 (Reasoning) scores 18.9 on the Artificial Analysis Intelligence Index, ranking 260th of 744 measured models. The closest models on this index are LongCat 2.0 (19.1), JT-35B-Flash (18.7), and Claude 4.1 Opus (18.6).

Artificial Analysis Indices
Reasoning
Intelligence18.9
Rank 260 of 744 measured models
Coding37.6
Rank 164 of 298 measured models
Math74.3
Rank 82 of 270 measured models
Standard Benchmarks
MMLU Pro84.2%
Rank 41 of 349 measured models
GPQA Diamond77.7%
Rank 231 of 619 measured models
HLE10.7%
Rank 324 of 664 measured models
LiveCodeBench65.5%
Rank 93 of 343 measured models
MATH-50099.1%
Rank 5 of 202 measured models
AIME 202477.3%
Rank 26 of 194 measured models
AIME 202574.3%
Rank 82 of 270 measured models
IFBench54.7%
Rank 154 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