ModelLab
ModelsCompare
ModelsLlama 4 Behemoth
∞

Llama 4 Behemoth

Meta

Meta's largest open-weights model, near-frontier quality.

FrontierOpen weightsVision
Lab page

Released

Apr 29, 2026

Context

1M

Pricing

Open

per 1M tok

Best at

Open weights

Performance

Benchmarks

Chatbot Arena
1469#6/17

Crowdsourced head-to-head chat preference Elo from LMArena. Captures perceived helpfulness and vibe across real-world prompts.

SWE-bench Verified
66.0#7/17

Share of real GitHub issues a model can autonomously resolve end-to-end (with tests passing). The de-facto agentic coding benchmark.

AIME 2025
92.5#7/16

American Invitational Mathematics Examination — competition math that rewards deep, multi-step reasoning. Reported as % solved.

GPQA Diamond
83.1#7/17

Google-proof graduate-level science Q&A (physics, biology, chemistry). PhD-level questions that resist web lookup.

MMLU-Pro
83.5#7/17

Harder, 10-way multiple-choice version of MMLU across 14 academic and professional domains. Breadth-of-knowledge signal.

Aider Polyglot
77.4#7/17

Editing a real codebase across multiple languages. Measures practical, instruction-following coding skill (not just generation).

OSWorld
28.5#8/16

Computer-use / agentic benchmark: completing real desktop OS tasks (apps, files, browsers). The leading autonomy metric.

Value score: 82/100

Quality-per-dollar blend of Chatbot Arena Elo against API price. Free / open models are scored against a floor.

Capabilities

  • Open weights
  • ~2T params
  • Self-hostable
TextVisionReasoningCode

Closest rivals

By Chatbot Arena Elo

  • DS

    DeepSeek V4

    DeepSeek

    1461
  • OA

    GPT-5.1

    OpenAI

    1458
  • A

    Claude Sonnet 4.6

    Anthropic

    1486

More from

Meta AI

∞

Llama 4 Maverick

MoE workhorse — efficient and openly deployable.

Data last checked Jun 9, 2026 (1mo ago)

ModelLab

An independent dashboard for comparing frontier AI models. Benchmark scores are drawn from public model cards, papers, and leaderboards. Always verify against the original source before making decisions.

Navigate

  • All models
  • Compare
  • About the data

Sources

  • LMArena ↗
  • SWE-bench ↗
  • LiveBench ↗

Data snapshot last checked June 17, 2026.

Not affiliated with any AI lab. Scores are approximations.