🇺🇸 United States🧠 GeneralistReleased April 2025
Llama 4 Behemoth
Meta
Open-sourceFreeSelf-host
Verdict
A solid pick for self-hosting and full data control.
Overview
Llama 4 Behemoth is Meta's largest model, natively multimodal with 1M context. The Llama Community license enables commercial use for organizations under 700M MAU. Ideal for enterprise-grade self-host setups. Much slower than closed frontiers.
Skill profile
Arena Elo1330
Verified benchmarks
GPQA66%
SWE-Bench45%
MATH86%
MMLU87%
HumanEval88.5%
What do these scores mean?
GPQA66%very good
PhD-level science questions (physics, chemistry, biology), with no tool access.
SWE-Bench45%fair
Resolving real GitHub issues under real conditions (SWE-bench Verified).
MATH86%excellent
Competition-level math problems.
MMLU87%excellent
General knowledge across dozens of academic subjects.
HumanEval88.5%excellent
Python code generation from specifications.
Strengths
- Excellent at code
- Strong French quality
- Very long context
- Has a free tier
Limitations
- Average speed
- No native GDPR guarantee
Who is it for
A good fit if…
- you want to control cost or self-host
- you work in French
Skip it if…
- you handle sensitive EU data
- you need very fast responses
Ideal use cases
- Large-scale pro self-host
- Academic research
- Multimodal long context
Access & availability
Paid API per tokenFree tier availableSelf-hostable (open weights)
Key specifications
Context
1M
Input price
$3.00 $/M
Output price
$9.00 $/M
Speed
40 tok/s
Price not auditedBenchmarks not audited
Estimate your monthly cost
Per-token API pricing$154/ month with Llama 4 Behemoth
For the same usage
- GPT-5$108-30%
- Claude Sonnet 4.6$196+28%
- Grok 4$256+67%
Indicative estimate based on standard API rates (excluding caching, batch and volume discounts). Always check the official pricing before committing.
Privacy
Not GDPR-compliantHosting : US/selfAnonymizable data
Advanced data · for expertsArchitecture, modalities, detailed cost, full benchmarks▾
Advanced data · for experts
Architecture, modalities, detailed cost, full benchmarks
Architecture
MoE
Size
~2T (288B actifs MoE)
Cutoff date
Nov 2024
Inputs
text, image
Outputs
text, code
License
llama-community
Hosting
US/self
Hallucination score
3/5
Estimated cost (API)
Typical exchange (~3k in / 1k out)
≈ $0.0180
1M in + 1M out
≈ $12.00
All benchmarks
| Arena Elo | 1330 |
| MMLU | 87.0% |
| GPQA | 66.0% |
| HumanEval | 88.5% |
| SWE-Bench | 45.0% |
| MATH | 86.0% |