Skip to catalog
FbFable
CatalogLabsScoresCompare
Catalog
A

Anthropic

Claude Opus 5

claude-opus-5

63Index
ClosedGenerally available1M contextTextImage

Pick this when

Hard work someone will sign. Agentic coding, long projects, detail-heavy writing.

Skip when

Routine volume. You are paying for thoroughness you may not need.

Leads the public Artificial Analysis Intelligence Index. Anthropic still recommends it as the starting point for complex agent work, even though Fable 5 is the named flagship.

Price

Input / 1M
$5.00
Output / 1M
$25
Measured task
$2.34

Flat rate through the full million-token window. Burns more tokens per job than Sol.

Shape

Context
1M
Max output
128K
Released
2026-07
Tools
Yes
Reasoning
Yes

Scores

Intelligence index63
GPQA Diamond92
Terminal-Bench 2.189
Agentic index56
Arena
2668
Speed
68/s
GPQA
92.4%
Term.
89.1%
  • AA Index. The single number most people mean by “how smart.” It is a blend, so a specialist can lose here and still win the job you care about.
  • GPQA. A clean test of hard reasoning. PhD experts sit around 65%. It says little about writing, tools, or taste.
  • Term.. Closest public proxy for coding agents that live in a terminal. A high index score with a weak terminal score is a warning.
  • Arena. Captures taste and usefulness that unit tests miss. Sample size varies by model, so treat gaps under ~100 Elo as noise.

Anthropic · San Francisco. Claude. Opus 5 leads public intelligence rankings. Fable 5 is the named flagship and the expensive one. Sonnet 5 is the daily driver.

Compiled 2026-08-28 from public Artificial Analysis, LMSYS-style arena, and first-party price sheets. Scores move. Recheck before you spend.

A two-point gap on the intelligence index is noise for most work. Cost per finished task is the number that shows up on the invoice.