Skip to main content

Llama 4 Maverick

MetaCurrentReleased Feb 28, 2026
Overall Score
Est. 17Prov. #115 of 119
Arena Elo
1043
Categories Ranked
8of 8
Price (1M tokens)
$0 in / $0 out
Speed
121tok/s
Context
1M
Open WeightSelf-hostNon-Reasoning
Confidence
base

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Llama 4 Maverick
API / mo$0
Self-host / mo$2,610
Break-even
Model the full break-even

According to BenchLM.ai, Llama 4 Maverick ranks #115 out of 119 models on the provisional leaderboard with an overall score of 17/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Llama 4 Maverick is a open weight model with a 1M token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

This profile currently has 17 of 225 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Reasoning (#68), while its weakest is Instruction Following (#106). This performance profile makes it particularly strong for complex reasoning, multi-step problem solving, and analytical tasks.

Ranking Distribution

Category rank across 8 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

#94
12.6/ 100
Weight: 22%4 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

#90
8.6/ 100
Weight: 20%3 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

#68
32.4/ 100
Weight: 17%2 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

#97
13.8/ 100
Weight: 12%6 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

#79
10.3/ 100
Weight: 5%0 benchmarks
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

#92
4.8/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

#79
34.2/ 100
Weight: 12%1 benchmark
MMMU-ProOfficeQA ProCharXivCharXiv w/o tools

Inst. Following

#106
22.7/ 100
Weight: 5%1 benchmark
IFEvalIFBench

Chatbot Arena Performance

Text Overall1043

Benchmark Details

Only benchmark rows with an attached exact-source record are shown here. Source-unverified manual rows and generated rows are hidden from model pages.

Frequently Asked Questions

How does Llama 4 Maverick perform overall in AI benchmarks?

Llama 4 Maverick currently ranks #115 out of 119 models on BenchLM's provisional leaderboard with an overall score of 17 (estimated). It is created by Meta and features a 1M context window.

Is Llama 4 Maverick good for knowledge and understanding?

Llama 4 Maverick ranks #97 out of 119 models in knowledge and understanding benchmarks with an average score of 13.8. There are stronger options in this category.

Is Llama 4 Maverick good for coding and programming?

Llama 4 Maverick ranks #90 out of 119 models in coding and programming benchmarks with an average score of 8.6. There are stronger options in this category.

Is Llama 4 Maverick good for reasoning and logic?

Llama 4 Maverick ranks #68 out of 119 models in reasoning and logic benchmarks with an average score of 32.4. There are stronger options in this category.

Is Llama 4 Maverick good for agentic tool use and computer tasks?

Llama 4 Maverick ranks #94 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 12.6. There are stronger options in this category.

Is Llama 4 Maverick good for multimodal and grounded tasks?

Llama 4 Maverick ranks #79 out of 119 models in multimodal and grounded tasks benchmarks with an average score of 34.2. There are stronger options in this category.

Is Llama 4 Maverick good for instruction following?

Llama 4 Maverick ranks #106 out of 119 models in instruction following benchmarks with an average score of 22.7. There are stronger options in this category.

Is Llama 4 Maverick open source?

Yes, Llama 4 Maverick is an open weight model created by Meta, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Does Llama 4 Maverick have full benchmark coverage on BenchLM?

Not yet. Llama 4 Maverick currently has 17 published benchmark scores out of the 225 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Llama 4 Maverick?

Llama 4 Maverick has a context window of 1M, which determines how much text it can process in a single interaction.

Last updated: June 2, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Don't miss the next GPT moment

Which models moved up, what’s new, and what it costs. One email a week, 3-min read.

Free. One email per week.