The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
Tested on 8 benchmarks · BenchGecko score 28.9. Top scores: MMLU (81.7%), MATH level 5 (41.6%), Fiction.LiveBench (33.3%).
Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.
Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.
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.
- Typetext
- Context131K tokens (~66 books)
- ReleasedDec 2024
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.000
Frequently Asked Questions
Key facts · as of 2026-07-11
- Llama 3.3 70B Instruct (free) by Meta. BenchGecko score 28.9, rank 252 of 312 scored models (normalized average of public benchmark scores).
- List price free input · free output per 1M tokens (as of 2026-07-11).
How to cite · data as of 2026-07-11
Llama 3.3 70B Instruct (free) · benchmarks, pricing and providers. BenchGecko, data as of 2026-07-11. https://benchgecko.ai/model/llama-3-3-70b-instruct-free
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