Back

Anthropic

Claude 3.7 Sonnet

Closed weights
Intelligence
15.3
Rank 305 of 744 measured models
Price/1M
$6
Rank 587 of 659 measured models
Context window
200K
Rank 618 of 1199 measured models

Claude 3.7 Sonnet (Non-reasoning) scores 15.3 on the Artificial Analysis Intelligence Index, ranking 305th of 744 measured models. The closest models on this index are Claude 4.5 Haiku (15.4), Kimi K2 0905 (15.3), and o1 (15.2). At $6 per million tokens (3:1 input/output blended price), it is cheaper than o1 ($26.25), more expensive than Claude 4.5 Haiku ($2) and Kimi K2 0905 ($1.08).

Artificial Analysis Indices
Non-reasoning
Intelligence15.3
Rank 305 of 744 measured models
Math21.0
Rank 209 of 270 measured models
Standard Benchmarks
MMLU Pro80.3%
Rank 111 of 349 measured models
GPQA Diamond65.6%
Rank 367 of 619 measured models
HLE4.2%
Rank 553 of 664 measured models
LiveCodeBench39.4%
Rank 186 of 343 measured models
MATH-50085.0%
Rank 95 of 202 measured models
AIME 202422.3%
Rank 99 of 194 measured models
AIME 202521.0%
Rank 209 of 270 measured models
IFBench44.0%
Rank 231 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