VerdictPal
Join

Models / Meta

Llama 4 Maverick

Llama 4 · Released 2026-04-05

Meta's reasoning-focused Llama 4 MoE. 1M context, 17B active / 400B total params, 128 experts. Open weights for multimodal assistants and coding.

Default Llama 4 pick for quality-first self-hosting when Scout's 10M context isn't required.

#43 of 51 on AA Index · current snapshot
14 AA Index · 21 benchmark rows · 6 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite49
Context1M
Input / 1M$0.17
Output / 1M$0.60
Knowledge cutoff2024-08-01
Output speed110 t/s
TTFT (default API)0.60s
Statusflagship
KnowledgeReasoningMathCodingAgenticMultimodalLong contextTool use
Knowledge
86
Reasoning
69
Math
89
Coding
92
Agentic
8
Multimodal
61
Long context
50
Tool use
76

66average across 8 tested families

Benchmark placements

Where Llama 4 Maverick places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
MATHMath#5/ 2089Artificial Analysis2026-07-21
MMMUMultimodal#6/ 861MMMU leaderboard2026-04-05
LiveCodeBenchCoding#10/ 1340Artificial Analysis2026-07-21
MMLU-ProKnowledge#11/ 2181Artificial Analysis2026-07-21
LongBench v2Long context#12/ 1950LongBench v2 leaderboard2026-04-01
LiveBenchReasoning#13/ 2162LiveBench leaderboard2026-04-15
HumanEvalCoding#14/ 1592Meta Llama 4 model card2026-04-05
BFCLTool use#15/ 2076Berkeley Function Calling Leaderboard V42026-04-15
AIMEMath#16/ 1919Artificial Analysis2026-07-21
MMLUKnowledge#19/ 2286Meta Llama 4 model card2026-04-05
SWE-bench VerifiedCoding#22/ 2375SWE-bench Verified leaderboard2026-06-09
AA output speedPerformance#24/ 69Artificial Analysis2026-07-21
IFBenchReasoning#53/ 5743Artificial Analysis2026-07-21
AA time to first tokenPerformance#54/ 69Artificial Analysis2026-07-21
AA-LCRLong context#56/ 6446Artificial Analysis2026-07-21
SciCodeCoding#58/ 6533Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#59/ 6714Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#61/ 655Artificial Analysis2026-07-21
GPQA DiamondReasoning#63/ 6969Artificial Analysis GPQA Diamond evaluation2026-06-09
τ³-Bench BankingAgentic#63/ 644Artificial Analysis2026-07-21
Terminal-BenchAgentic#66/ 698Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models in each capability family. Where Llama 4 Maverick shows up, it's highlighted.

KnowledgeLlama 4 Maverick · 86
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningLlama 4 Maverick · 69
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
MathLlama 4 Maverick · 89
  1. 1
    OpenAI o3
    99
  2. 2
    OpenAI o1
    97
  3. 3
    Gemini 3 Pro
    96
CodingLlama 4 Maverick · 92
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticLlama 4 Maverick · 8
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
MultimodalLlama 4 Maverick · 61
  1. 1
    Gemini 3.1 Pro
    72
  2. 2
    GPT 5.5
    72
  3. 3
    Claude Opus 4.8
    71
Long contextLlama 4 Maverick · 50
  1. 1
    Kimi K3
    75
  2. 2
    GPT-5.1
    75
  3. 3
    GPT-5.6 Sol
    74
Tool useLlama 4 Maverick · 76
  1. 1
    Claude Sonnet 4.6
    89
  2. 2
    GPT 5.5
    87
  3. 3
    Claude Opus 4.8
    87
Newest receipts

Benchmark rows added to the public ledger for Llama 4 Maverick in the last 120 days. Older rows live in the full table below.

21 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context46%Artificial Analysis2
AA output speedPerformance110 t/sArtificial Analysis2
AA time to first tokenPerformance0.60sArtificial Analysis2
AIMEMath19.33%Artificial Analysis2
Artificial Analysis Intelligence IndexReasoning14.3%Artificial Analysis2
Humanity's Last ExamReasoning4.8%Artificial Analysis2
IFBenchReasoning42.99%Artificial Analysis2
LiveCodeBenchCoding39.7%Artificial Analysis2
MATHMath88.87%Artificial Analysis2
MMLU-ProKnowledge80.9%Artificial Analysis2
SciCodeCoding33.1%Artificial Analysis2
τ³-Bench BankingAgentic3.92%Artificial Analysis2
Terminal-BenchAgentic7.87%Artificial Analysis2
SWE-bench VerifiedCoding74.8%SWE-bench Verified leaderboard44
GPQA DiamondReasoning69.4%Artificial Analysis GPQA Diamond evaluation44
BFCLTool use75.9%Berkeley Function Calling Leaderboard V499
LiveBenchReasoning62.1%LiveBench leaderboard99
HumanEvalCoding91.8% pass@1Meta Llama 4 model card109
MMLUKnowledge86.1%Meta Llama 4 model card109
MMMUMultimodal61.4%MMMU leaderboard109
LongBench v2Long context49.8%LongBench v2 leaderboard113
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Knowledge86
Reasoning69
Math89
Coding92
Agentic8
Multimodal61
Long context50
Tool use76
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere

Full benchmark ledger

Every catalog benchmark for Llama 4 Maverick. Scores link to the original source; gaps mean no public row exists yet.

21 sourced rows

21 of 32 catalog benchmarks have a sourced row for Llama 4 Maverick.

Knowledge

Reasoning

Math

Coding

Agentic

Multimodal

Long context

Tool use

Performance

Sources