> Claude Sonnet 5.5 is a closed AI model from Anthropic, released 28 Sep 2026. Index score 193 (GPT-4 = 100), rank 3 of 229 ranked models. API price $2.0 in / $10 out per million tokens, 1M context.

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

# Claude Sonnet 5.5

Anthropic

Released 28 Sep 2026

Closed

Flagship

Date verified

[Compare](https://themodelindex.org/compare/claude-sonnet-5-5-vs-kimi-k3/) [Announcement](https://www.anthropic.com/claude-sonnet-5-5)

193182–205

Index score

#3 of 229 models

3/ 8

Core tests taken

3 of 6 areas · plus 8 anchor tests

−7

Versus the frontier at release

best then: Claude Opus 5.5

$2.0/ $10

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-6 Astra reached this score 1 month earlier.

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

Show 7 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

96%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

89%

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

76%

Novel problems

no evidence yet

ARC-AGI-2

no result

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

#3

of 219 · 193

Artificial Analysis Intelligence Index

overall capability across ten evaluations

#2

of 207 · 56

Epoch Capabilities Index

overall capability from many benchmarks

#3

of 239 · 165.2

LMArena · WebDev

building web apps and front ends

#5

of 123 · 1709

LiveBench · Overall

overall, with fresh questions to limit contamination

#19

of 58 · 77.8

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

1st

APEX-Agents

Epoch AI · independent

2nd

coding questions

LiveBench · Coding

2nd

GPQA Diamond

Epoch AI · independent

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

G

Google

$2.2 / $11

cheapest

A

Amazon Bedrock

$2.0 / $10

↗

A

Azure

$2.2 / $11

↗

C

Claude Platform on AWS

$2.0 / $10

↗

A

Anthropic

$2.0 / $10

↗

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 Sep 2026

Announcement

[anthropic.com ↗](https://www.anthropic.com/claude-sonnet-5-5)

Release entry

Claude Sonnet 5.5

Scored as

Claude Sonnet 5.5

Artificial Analysis index

56 · max with fallback

Output speed

139 tokens/s

Hugging Face

closed weights

## Anthropic releases · around this one

Claude Mythos 5.1

Closed

1 SEP 2026

Claude Opus 5.5

Closed

22 SEP 2026

index 200

Claude Sonnet 5.5

Closed

28 SEP 2026

index 193

---
Source: https://themodelindex.org/models/claude-sonnet-5-5/ · The Model Index · data as of 2026-10-01