> Claude Haiku 4.5 is a closed AI model from Anthropic, released 15 Oct 2025. Index score 137 (GPT-4 = 100), rank 98 of 229 ranked models. API price $1.0 in / $5.0 out per million tokens, 200K context.

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

# Claude Haiku 4.5

Anthropic

Released 15 Oct 2025

Closed

Small / fast

Date verified

[Compare](https://themodelindex.org/compare/claude-haiku-4-5-vs-kimi-k2-thinking/) [Announcement](https://www.anthropic.com/news/claude-haiku-4-5)

137125–148

Index score

#98 of 229 models

3/ 8

Core tests taken

3 of 6 areas · plus 13 anchor tests

−17

Versus the frontier at release

best then: GPT-5

$1.0/ $5.0

Price per million tokens

input / output, list price

200K

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_

Gemini 2.5 Pro reached this score 7 months earlier.

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

Show 11 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

71%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

no result

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

36%

Agents

evidence

APEX-Agents

no result

Novel problems

evidence

ARC-AGI-2

4%

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

#98

of 219 · 137

Artificial Analysis Intelligence Index

overall capability across ten evaluations

#65

of 207 · 17

Epoch Capabilities Index

overall capability from many benchmarks

#95

of 239 · 142.4

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

Not in the top three among current models on any category we track.

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 · 4 · per million tokens, in / out

A

Azure

$1.0 / $5.0

cheapest

A

Amazon Bedrock

$1.1 / $5.5

↗

G

Google

$1.1 / $5.5

↗

A

Anthropic

$1.0 / $5.0

↗

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

15 Oct 2025

Announcement

[anthropic.com ↗](https://www.anthropic.com/news/claude-haiku-4-5)

Release entry

Claude Haiku 4.5

Scored as

Claude Haiku 4.5

Artificial Analysis index

–

Output speed

–

Hugging Face

closed weights

## Anthropic releases · around this one

Claude Opus 4.1

Closed

5 AUG 2025

index 140

Claude Sonnet 4.5

Closed

29 SEP 2025

index 146

Claude Haiku 4.5

Closed

15 OCT 2025

index 137

Claude Opus 4.5

Closed

24 NOV 2025

index 153

Claude Opus 4.6

Closed

5 FEB 2026

index 167

---
Source: https://themodelindex.org/models/claude-haiku-4-5/ · The Model Index · data as of 2026-10-01