MDL
Llama 4 Maverick
Meta
Verified against Artificial Analysis · Jul 13, 2026
Capability
54
percentile index
Price /M
$0.35 / $0.85
in / out
Context
1M
tokens
Avg score
40.7
11 benchmarks
AA Intelligence
14.3
index
Speed
117 tok/s
TTFT 0.6s
Released
Apr 5, 2025
About
Llama 4 Maverick is a open-weights model in the Llama family from Meta. Benchmarked on 11 evals, averaging 40.7.
Benchmark scores · 11
avg 40.7 — higher is betterThe research behind this model
all papers mentioning it →FORGE: Self-Evolving Agent Memory With No Weight Updates via Population BroadcastMay 15, 2026Hybrid LLM-based Intelligent Framework for Robot Task SchedulingMay 15, 2026Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information ExtractionMay 14, 2026SPIN: Structural LLM Planning via Iterative Navigation for Industrial TasksMay 13, 2026Three Regimes of Context-Parametric Conflict: A Predictive Framework and Empirical ValidationMay 12, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed117 tok/s
Latency (TTFT)0.6s
Price in / out$0.35 / $0.85 per 1M
Blended price$0.475 / 1M
Coding index16.3
Math index19.3
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0.85/M