The Model Index
Models/Anthropic

Claude Opus 4.8

AnthropicClosed weightsFlagship

Claude Opus 4.8 is a closed AI model from Anthropic with an index score of 170 (GPT-4 = 100), rank 26 of 217.

170154–186Index score#26 of 217 models
$5.0/ $25Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
28 May 2026ReleasedReplaced by Claude Opus 5

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100Claude Opus 4.8

GPT-5.5 reached this score 1 month earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond (Epoch AI)
91%
Humanity's Last Exam
no result
Mathsevidence
FrontierMath (tiers 1-3)
80%
Codingevidence
SWE-bench Verified
no result
Terminal-Bench 4.0
23%
Agentsevidence
APEX-Agents
49%
Professional workevidence
Finance Agent (v2)
54%
Novel problemsevidence
ARC-AGI-2
72%
Long tasksno evidence yet
METR time horizon
no result

Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.

What others sayrank on 12 leaderboards

Best attop three among current models

Where to use itprices checked 18 Nov 2026

Host prices from OpenRouter; going direct can differ.

Facts and sources

Released28 May 2026
Announcementanthropic.com ↗
Release entryClaude Opus 4.8
Scored asClaude Opus 4.8
Output speed–
Hugging Faceclosed weights

Anthropic releasesaround this one

This page as a chartDownload PNG