Llama 4 Maverick

Llama 4 Maverick is a non-reasoning model from Meta. 19 benchmarks count toward its score, in 7 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.33.6 ±4.2
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.3/s
Input / 1MUS dollars per 1M input tokens.$0.188
Output / 1MUS dollars per 1M output tokens.$0.653
ContextMaximum tokens in one request.1.05M
EloLMArena rating and rank.N/A

50 is the middle of the board. The range shows the doubt in the index.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
28.3
CodingCode writing and repair.
33.7
ReasoningLogic problems and puzzles.
37.6
MultimodalTasks with images and text.
43.0
KnowledgeFacts and expert knowledge.
37.4
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
32.7
MathMath problems.
29.7

Results

19 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result on the index scale.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
MATH level 5Math73.0%34.6Epoch AI
Artificial Analysis GPQA DiamondKnowledge67.1%37.3Artificial Analysis
GPQA diamondKnowledge67.0%40.1Epoch AI
Artificial Analysis MMMU-ProMultimodal62.1%43.0Artificial Analysis
Artificial Analysis Long Context ReasoningReasoning50.0%42.8Artificial Analysis
Artificial Analysis IFBenchInstruction43.0%32.7Artificial Analysis
Artificial Analysis SciCodeCoding31.7%36.9Artificial Analysis
Artificial Analysis Omniscience AccuracyKnowledge24.9%44.7Artificial Analysis
OTIS Mock AIME 2024-2025Math20.6%23.1Epoch AI
τ²-Bench Tool-Agent-User EvaluationAgentic17.8%11.6Victor Barres et al.
Artificial Analysis Coding IndexCoding16.3%30.4Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge10.0%34.9Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge4.9%29.9Artificial Analysis
ARC-AGI-1 (semi-private)Reasoning4.4%29.3ARC Prize Foundation
FrontierMath-2025-02-28-PrivateMath0.7%31.3Epoch AI
Artificial Analysis Agentic IndexAgentic0.6%37.7Artificial Analysis
GDPval-AA normalizedAgentic0.0%35.6Artificial Analysis
Critical Physics TasksReasoning0.0%38.4Artificial Analysis
ARC-AGI-2 (semi-private)Reasoning0.0%39.7ARC Prize Foundation

19 benchmarks count, from 19 of 19 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence statedEpoch AI, collected directlyCC BY — free to use and redistribute with attributionARC Prize Foundation, collected directlyNo licence stated. Their terms ask for written permission before commercial use

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from Meta

Muse Spark 1.375.0Muse Spark 1.269.2Muse Spark 1.167.0Muse Spark61.6Muse Glimmer 30B53.5