Inference
EN
Meta

Llama4 Maverick Instruct Basic

Llama4 Maverick Instruct Basic is a model from Meta. 8 benchmarks count toward its index, in 5 categories.

  • Input: text
RankedEnough results for an index.
IndexAll categories, out of 100.36.0±8.2Median 51.0
CoverageIndex weight that has results.75%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.—Median 262K
EloLMArena rating and rank.—Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.2 counted29.4203 / 218
CodingCode writing and repair.1 counted28.5—
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.1 counted48.5—
KnowledgeFacts and expert knowledge.2 counted42.7180 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.2 counted30.3142 / 168

Results

8 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
MATH 500Math85.2% ±1.635 / 59
MMLU ProKnowledge79.4% ±0.495 / 135
GPQA Diamond · Vals AIKnowledge69.4% ±2.495 / 135
MMMU ProMultimodal71.7% ±1.167 / 92
AIMEMath25.2% ±0.878 / 95
LiveCodeBenchCoding47.3% ±1.2118 / 142
Terminal-Bench 1.0Agentic17.5% ±4.243 / 47
Terminal-Bench 2.0 · Vals AIAgentic2.2% ±1.665 / 66
MGSMMultilingual92.4% ±1.618 / 74
LegalBenchLegal77.8% ±0.4106 / 149
MortgageTaxFinance58.5% ±1.070 / 97
MedCodeHealthcare36.5% ±2.077 / 106
TaxEval v2Finance66.6% ±0.9110 / 143
CorpFin v2Finance49.7% ±1.0109 / 131
MedScribeHealthcare54.2% ±1.9107 / 109
MedQAHealthcare43.3% ±0.594 / 95

Sources

BenchLMCC BY-NC 4.0Vals AINo licence stated

History

5 releases
Index37.0 → 36.0
23 Oct 202612 Nov 2026

Questions

How good is Llama4 Maverick Instruct Basic?
Its index is 36.0 out of 100. That is place 233 of 283 ranked models.
What is Llama4 Maverick Instruct Basic best at?
Knowledge: 42.7 out of 100, place 180 of 268.

Badge

Llama4 Maverick Instruct Basic on Inference360: place 233 of 283, index 36.0
HTML
<a href="https://inference360.ai/models/meta-llama4-maverick-instruct-basic"><img src="https://inference360.ai/badges/meta-llama4-maverick-instruct-basic.svg" alt="Llama4 Maverick Instruct Basic on Inference360: place 233 of 283, index 36.0" height="20"></a>
Markdown
[![Llama4 Maverick Instruct Basic on Inference360: place 233 of 283, index 36.0](https://inference360.ai/badges/meta-llama4-maverick-instruct-basic.svg)](https://inference360.ai/models/meta-llama4-maverick-instruct-basic)

Compare with

Grok 4.1 Fast Non Reasoning36.2

More from Meta

All models
Muse Wonder Full77.3Muse Wonder73.1Muse Spark 1.370.1Muse Spark Open65.1Muse Spark 1.264.9