Anthropic

Claude Opus 5.5 (Default Fallback)

Intelligence
51.8
Rank 18 of 788 measured models
Output speed
106 t/s
Rank 153 of 454 measured models
Price/1M
$8
Rank 673 of 741 measured models
Context window
1M
Rank 107 of 1334 measured models
Cost per task
$3.46
Rank 195 of 235 measured models

Claude Opus 5.5 (High, Default Fallback) scores 51.8 on the Artificial Analysis Intelligence Index, ranking 18th of 788 measured models. The closest models on this index are GPT-6.1 Terra (51.3), Gemini 4 Argon (50.4), and Muse Wonder Full (Max) (50.1). At $8 per million tokens (3:1 input/output blended price), it is priced close to Gemini 4 Argon ($8), more expensive than GPT-6.1 Terra ($2). With an output speed of 106 t/s, it is faster than GPT-6.1 Terra (68 t/s) and Gemini 4 Argon (65 t/s).

Artificial Analysis Indices
High
Intelligence51.8
Rank 18 of 788 measured models
Reasoning levels
Each point is a reasoning level of this model: more reasoning often raises the score but costs more. Select a point to open that level.
Intelligence Indexmost efficient ↗Cost per task
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting53.3
Rank 26 of 260 measured models
Strategy & Ops57.6
Rank 16 of 260 measured models
Legal52.0
Rank 25 of 260 measured models
Healthcare & Medical52.5
Rank 9 of 190 measured models
Engineering57.8
Rank 17 of 259 measured models
Economics55.3
Rank 20 of 267 measured models
Standard Benchmarks
HLE55.6%
Rank 8 of 682 measured models
SciCode60.4%
Rank 12 of 249 measured models
AA-LCR82.7%
Rank 36 of 593 measured models
Terminal-Bench 4.056.6%
Rank 14 of 246 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