All Comparisons

Llama 4 Maverick vs o4-mini

M
Llama 4 Maverick
Meta πŸ‡ΊπŸ‡Έ
51.2
#173β€”
low
$0.20/M in Β· $0.80/M out
1.0M context
o4-mini
OpenAI πŸ‡ΊπŸ‡Έ
57.1
#155β€”
high
Most Affordable
Llama 4 Maverick
$0.20/M input
Largest Context
Llama 4 Maverick
1.0M tokens
Best Benchmark Score
o4-mini
57.1/100

Model Specifications

SpecLlama 4 Mavericko4-mini
ProviderMetaOpenAI
Release DateApr 2025Apr 2025
Knowledge Cutoffβ€”2024-05-31
Parameters400000000000BUndisclosed
Context Window1.0Mβ€”
Max Outputβ€”β€”
Open SourceYesNo
Licensellama_4_community_license_agreementproprietary
Tokenizerβ€”β€”
Modalityβ€”β€”
Reasoning ModelNoNo
ModeratedNoNo

Pricing Comparison

Price (per 1M tokens)Llama 4 Mavericko4-mini
Input$0.20β€”
Output$0.80β€”

API Provider Pricing

Capabilities

FeatureLlama 4 Mavericko4-mini
Text Input
Image Input (Vision)
Audio Input
Video Input
File Input
Image Output
Audio Output
Tool Use
Structured Output (JSON)
Streaming
Reasoning Tokens
Web Search
Temperature Control
Top-P Sampling
Stop Sequences
Seed (Reproducibility)
Log Probabilities

Category Comparison

Benchmark-by-Benchmark

reasoning

BenchmarkLlama 4 Mavericko4-mini
GPQA Diamond
69.8
81.4
Humanity's Last Examβ€”
14.7

multimodal

BenchmarkLlama 4 Mavericko4-mini
MMMU
73.4
81.6
MMMU-Pro
59.6
β€”
CharXiv Reasoningβ€”
72

coding

BenchmarkLlama 4 Mavericko4-mini
SWE-bench Verifiedβ€”
68.1

math

BenchmarkLlama 4 Mavericko4-mini
AIME 2025β€”
92.7

agent

BenchmarkLlama 4 Mavericko4-mini
BrowseCompβ€”
51.5
TAU-Bench Retailβ€”
71.8

Category Winners

coding
o4-mini
56.0
math
o4-mini
74.3
reasoning
M
Llama 4 Maverick
53.9
multimodal
o4-mini
62.5
agent
o4-mini
43.4

Compare More Models

Frequently Asked Questions