Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...
Tested on 11 benchmarks · BenchGecko score 11.7. Top scores: Chatbot Arena Elo — Overall (1111.1%), IFEval (58.1%), BBH (HuggingFace) (8.3%).
HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.
HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.
Broad Assessment of Language and Reasoning Over Games. Tests strategic and logical reasoning through game scenarios.
HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.
- Typetext
- Context60K tokens (~30 books)
- ReleasedSep 2024
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.000
Frequently Asked Questions
Key facts · as of 2026-10-05
- Llama 3.2 1B Instruct by Meta. BenchGecko score 11.7, rank 297 of 312 scored models (normalized average of public benchmark scores).
- List price $0.0270 input · $0.20 output per 1M tokens (as of 2026-10-05).
- Sold by 1 provider (as of 2026-10-05): Cloudflare $0.0270 in / $0.20 out.
How to cite · data as of 2026-10-05
Llama 3.2 1B Instruct · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/llama-3-2-1b-instruct
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