Back

Anthropic

Claude 3.5 Sonnet (Oct '24)

Closed weights
Intelligence
7.9
Rank 506 of 744 measured models
Coding
30.2
Rank 184 of 298 measured models
Price/1M
$6
Rank 587 of 659 measured models
Context window
200K
Rank 618 of 1199 measured models

Claude 3.5 Sonnet (Oct '24) scores 7.9 on the Artificial Analysis Intelligence Index, ranking 506th of 744 measured models. The closest models on this index are DeepSeek R1 Distill Llama 70B (7.9), Gemini 1.5 Pro (Sep '24) (7.9), and Qwen3 VL 30B A3B Instruct (7.9). At $6 per million tokens (3:1 input/output blended price), it is more expensive than DeepSeek R1 Distill Llama 70B ($0.80) and Qwen3 VL 30B A3B Instruct ($0.412).

Artificial Analysis Indices
Intelligence7.9
Rank 506 of 744 measured models
Coding30.2
Rank 184 of 298 measured models
Standard Benchmarks
MMLU Pro77.2%
Rank 155 of 349 measured models
GPQA Diamond59.9%
Rank 406 of 619 measured models
HLE3.7%
Rank 611 of 664 measured models
LiveCodeBench38.1%
Rank 189 of 343 measured models
MATH-50077.1%
Rank 118 of 202 measured models
AIME 202415.7%
Rank 110 of 194 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