What are Llama 4 Maverick Basic's benchmark scores?

As of 25 Oct 2026, Llama 4 Maverick Basic scores 39.4 ±10.6 on the BenchLeader Index, strongest in maths (45) and weakest in knowledge (32). That rests on 10 independent benchmark results, and every score on this page links to its publisher.

How does Llama 4 Maverick Basic rank?

Llama 4 Maverick Basic is #686 of 785 ranked configurations on 25 Oct 2026. 399 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

Meta Compare with another model

Llama 4 Maverick Basic

Llama 4 Maverick Basic is a Meta proprietary model. Its best configuration ranks #686 of 785 on the BenchLeader Index at 39.4 ±10.6, in the lower half. The ± is the point: 399 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in maths (45) and lowest in knowledge (32). Last measured 13 Oct 2026.

Blended price: –
Output speed: –
First answer: –
Context: –
Full answer: –
Cost per run: –
Released: –; date not published by our sources

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index39
Coding32
Maths45
Knowledge32

How its index has moved

9 Sept 2026 to 14 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	not stated	Source
GPQA Diamond (Vals)not in index	69.4%#91	Vals AI

Coding

Benchmark	not stated	Source
LiveCodeBench	47.3%#113	Vals AI

Agents & tools

Benchmark	not stated	Source
Poker Agentnot in index	890.5%#16	Vals AI
Terminal-Bench 2.0 (Vals)not in index	2.3%#63	Vals AI

Maths

Benchmark	not stated	Source
AIME (Vals)	25.2%#75	Vals AI
MGSM	92.4%#18	Vals AI
MATH 500not in index	85.2%#33	Vals AI

Knowledge

Benchmark	not stated	Source
MMLU-Pro	79.4%#91	Vals AI
LegalBench	77.8%#102	Vals AI
CorpFin	49.7%#103	Vals AI
TaxEval	66.6%#106	Vals AI
MedQA	43.3%#90	Vals AI
PRBench Finance	22.4%#37	Scale AI SEAL
PRBench Legal	24.8%#42	Scale AI SEAL
MedCodenot in index	36.5%#75	Vals AI
MedScribenot in index	54.2%#103	Vals AI

Multimodal

Benchmark	not stated	Source
MMMU-Pro (Vals)not in index	71.7%#65	Vals AI
MortgageTaxnot in index	58.5%#67	Vals AI
SAGEnot in index	35.7%#66	Vals AI

New this month

Questions people ask

What are Llama 4 Maverick Basic's benchmark scores?: As of 25 Oct 2026, Llama 4 Maverick Basic scores 39.4 ±10.6 on the BenchLeader Index, strongest in maths (45) and weakest in knowledge (32). That rests on 10 independent benchmark results, and every score on this page links to its publisher.
How does Llama 4 Maverick Basic rank?: Llama 4 Maverick Basic is #686 of 785 ranked configurations on 25 Oct 2026. 399 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Llama 4 Maverick Basic: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/llama-4-maverick-basic.