The Model Index
Models/Meta

Llama 4 Maverick

MetaOpen weights

Llama 4 Maverick is an open-weights AI model from Meta with an index score of 116 (GPT-4 = 100), rank 165 of 217.

116100–132Index score#165 of 217 models
$0.35/ $1.0Price per million tokensinput / output · via OpenRouter
524KContext windowtokens it reads at once
5 Apr 2025Released1 year 7 months ago

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100Llama 4 Maverick

o1-mini reached this score 7 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond (Epoch AI)
67%
Humanity's Last Exam
6%
Mathsevidence
FrontierMath (tiers 1-3)
no result
Codingevidence
SWE-bench Verified
no result
Terminal-Bench 4.0
no result
Agentsevidence
APEX-Agents
no result
Professional workevidence
Finance Agent (v2)
no result
Novel problemsevidence
ARC-AGI-2
0%
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 2 leaderboards

The Model Indexthird-party tests, our method#165of 217 · 116
Epoch Capabilities Indexoverall capability from many benchmarks#138of 231 · 132.2

Best attop three among current models

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

Where to use itprices checked 18 Nov 2026

Host prices from OpenRouter; going direct can differ.

Facts and sources

Released5 Apr 2025
Announcementabout.fb.com ↗
Release entryLlama 4 (Scout/Maverick)
Scored asLlama 4 Maverick
Output speed–

Meta releasesaround this one

This page as a chartDownload PNG