> Claude Opus 4.8 is a closed AI model from Anthropic, released 28 May 2026. Index score 174 (GPT-4 = 100), rank 12 of 229 ranked models. API price $5.0 in / $25 out per million tokens, 1M context.

[Models](https://themodelindex.org/models/) /[Anthropic](https://themodelindex.org/labs/anthropic/)

# Claude Opus 4.8

Anthropic

Released 28 May 2026

Closed

Flagship

Date verified

[Compare](https://themodelindex.org/compare/claude-opus-4-8-vs-glm-5-2/) [Announcement](https://www.anthropic.com/research/claude-opus-4-8)

174163–185

Index score

#12 of 229 models

4/ 8

Core tests taken

4 of 6 areas · plus 21 anchor tests

−3

Versus the frontier at release

best then: GPT-5.5

Replaced by [Claude Opus 5](https://themodelindex.org/models/claude-opus-5/)

$5.0/ $25

Price per million tokens

input / output, list price

1M

Context window

tokens it reads at once

## Where it sits · on the frontier

_Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_

GPT-5.5 reached this score 1 month earlier.

## Test results · by area · tick = best by any model

Show 15 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

91%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

80%

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

49%

Novel problems

evidence

ARC-AGI-2

72%

Long tasks

no evidence yet

METR time horizon

no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

## What others say · rank on each leaderboard

The Model Index

independent tests, our method

#12

of 219 · 174

Epoch Capabilities Index

overall capability from many benchmarks

#12

of 239 · 158.3

LiveBench · Overall

overall, with fresh questions to limit contamination

#25

of 58 · 76.2

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.

## Best at · top three among current models

Replaced by Claude Opus 5; it no longer leads any category among current models.

Where this model places in the top three of today's models, on category leaderboards and on our core tests.

## Where to use it · prices checked 1 Oct 2026

#### From the lab

Claude

app · subscription

↗

Claude API

API

↗

#### API providers · 5 · per million tokens, in / out

C

Claude Platform on AWS

$5.0 / $25

cheapest

A

Azure

$5.5 / $27.5

↗

A

Amazon Bedrock

$5.5 / $27.5

↗

G

Google

$5.5 / $27.5

↗

A

Anthropic

$10 / $50

↗

Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps.

## Facts and sources

Released

28 May 2026

Announcement

[anthropic.com ↗](https://www.anthropic.com/research/claude-opus-4-8)

Release entry

Claude Opus 4.8

Scored as

Claude Opus 4.8

Artificial Analysis index

–

Output speed

–

Hugging Face

closed weights

## Anthropic releases · around this one

Claude Mythos Preview

Closed

7 APR 2026

Claude Opus 4.7

Closed

16 APR 2026

index 169

Claude Opus 4.8

Closed

28 MAY 2026

index 174

Claude Fable 5

Closed

9 JUN 2026

index 185

Claude Mythos 5

Closed

9 JUN 2026

---
Source: https://themodelindex.org/models/claude-opus-4-8/ · The Model Index · data as of 2026-10-01