Back
FR

Model creator

Anthropic

Every Anthropic model in the BenchSift catalogue, with its scores, ranks, prices and capabilities as the sources publish them.

View in the catalogue
Models
47
87 configurations, reasoning levels included
Open weights
0
0 of 47 models
Latest release
Nov 9, 2026
Claude Fable 5.2 (High, Default Fallback) · First dated model: Mar 14, 2023
Median price
$6
$0.20 to $30 per million tokens, across 25 priced models

Best scores and ranks

The creator's best model on each measure, and its rank among every measured model in the catalogue.

Intelligence

Claude Fable 5.2 (Max, Default Fallback)
64.6Rank 1 of 782 measured models

Coding

Claude Fable 5.1 (Max, Default Fallback)
80.7Rank 1 of 301 measured models

Math

Claude Opus 4.5 (Reasoning)
91.3Rank 20 of 270 measured models

Agentic

Claude Fable 5.1 (Max, Default Fallback)
57.2Rank 1 of 191 measured models

Output speed

Claude Haiku 5.5 (Max)
255 t/sRank 17 of 449 measured models

Lowest price

Claude Haiku 5.5 (High)
$0.20Rank 190 of 740 measured models

OpenRouter ranking

Claude Opus 5.5 (Max, Default Fallback)
#7

Capabilities

Number of models that declare each capability. Tool calling and structured outputs come from OpenRouter.
Reasoning35 of 47
Open weights0 of 47
Tool calling25 of 47
Structured outputs21 of 47

Input

  • Text47
  • Image44
  • Files24

Output

  • Text47

Overview

Model types

  • Text47

Releases by year

  • 202619
  • 202516
  • 20249
  • 20233

Models

47

Reasoning levels are folded into one entry. The rank is the whole catalogue's: sorting does not change it.

Where these figures come from

Each catalogue model is tied to its creator by the identity Artificial Analysis publishes, or OpenRouter's and Models.dev's for models it does not track. Counts fold the reasoning levels of one model together. Ranks compare each measure with every measured model in the catalogue, configurations included, as model pages do. The price is the published blended price (3 input tokens to 1 output token).

Figures computed by BenchSift from the catalogue: Artificial Analysis, OpenRouter, Models.dev and Hugging Face. A value no model carries is not shown.

Data retrieved on Nov 12, 2026.

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