Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
Tested on 29 benchmarks · BenchGecko score 22.1. Top scores: MATH level 5 (73.0%), Artificial Analysis · GPQA Diamond (67.1%), Artificial Analysis · MMMU Pro (62.1%).
Gemma 3 27B scores 22.7 (103% as good) at $0.08/1M input · 57% cheaper
Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.
SWE-bench Verified solved using only bash commands, no specialized frameworks. Tests raw terminal-based problem solving.
Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.
Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.
Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.
ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.
Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
Original research-level math problems created by professional mathematicians. Problems are unpublished and cannot be memorized.
- Typemultimodal
- Context1.0M tokens (~524 books)
- ReleasedApr 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.001
Frequently Asked Questions
Related Models
Claude 2.1 · AnthropicGPT-4.1 Nano · OpenAIMistral Small 3.1 24B · Mistral AIGemma 3 27B · Google DeepMindLlama 2 7b Hf · MetaKey facts · as of 2026-10-05
- Llama 4 Maverick by Meta. BenchGecko score 22.1, rank 275 of 312 scored models (normalized average of public benchmark scores).
- List price $0.19 input · $0.65 output per 1M tokens (as of 2026-10-05).
- Sold by 4 providers (as of 2026-10-05): DigitalOcean $0.19 in / $0.65 out · Novita (fp8) $0.27 in / $0.85 out · Google $0.35 in / $1.15 out · Parasail (fp8) $0.35 in / $1.00 out. Every provider
- Gecko Tests · Gecko Score 20 (rank 12): Who Are You E (Sometimes says it is Google or OpenAI) · World Map E (79.2% of the map right) · Tokenizer Tax B (44% more tokens outside English).
How to cite · data as of 2026-10-05
Llama 4 Maverick · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/llama-4-maverick
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP