Back

Anthropic

Claude 3 Haiku

Closed weights
Intelligence
5.6
Rank 663 of 744 measured models
Price/1M
$0.50
Rank 277 of 659 measured models
Context window
200K
Rank 618 of 1199 measured models

Claude 3 Haiku scores 5.6 on the Artificial Analysis Intelligence Index, ranking 663rd of 744 measured models. The closest models on this index are Claude 2.1 (5.6), Molmo 7B-D (5.6), and Reka Flash 3 (5.6). At $0.50 per million tokens (3:1 input/output blended price), it is more expensive than Reka Flash 3 ($0.35).

Artificial Analysis Indices
Intelligence5.6
Rank 663 of 744 measured models
Standard Benchmarks
GPQA Diamond37.4%
Rank 538 of 619 measured models
HLE4.1%
Rank 567 of 664 measured models
LiveCodeBench15.4%
Rank 289 of 343 measured models
MATH-50039.4%
Rank 185 of 202 measured models
AIME 20241.0%
Rank 174 of 194 measured models
IFBench36.1%
Rank 325 of 450 measured models
AA-LCR27.7%
Rank 418 of 575 measured models
TerminalBench Hard0.8%
Rank 370 of 432 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