# Meta Llama 3.2 1B Instruct

As of October 22, 2026, Meta Llama 3.2 1B Instruct ranks #123 of 123 models overall with 9.6 ±3.4 on the LLMBenchmark Index. Llama 3.2 1B Instruct ranks #116 of 122 in reasoning, its strongest category. Meta Llama 3.2 1B Instruct costs $0.027 per million input tokens and $0.201 per million output tokens. Llama 3.2 1B Instruct was released on September 25, 2024.

Page: https://llmbenchmark.ai/models/llama-3-2-1b-instruct
Data from October 22, 2026. Every figure below names the board it was read from and the day.

- Maker: Meta Llama
- Released: September 25, 2024
- Price per million input tokens: $0.027
- Price per million output tokens: $0.201
- Context window: 60K tokens
- Overall rank: 123 of 123, by the LLMBenchmark Index
- LLMBenchmark Index: 9.6 ±3.4 (90% margin, from 4 of 7 inputs)
- Artificial Analysis Intelligence Index: 4.8

Benchmark results (38 of 195):

- AA Intelligence Index: 4.8 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Math Index: 0.0 (source: Artificial Analysis, read October 22, 2026)
- GPQA Diamond (Artificial Analysis run): 19.6% (source: Artificial Analysis, read October 22, 2026)
- Humanity's Last Exam (Artificial Analysis run): 5.5% (source: Artificial Analysis, read October 22, 2026)
- MMLU Pro (Artificial Analysis run): 20.0% (source: Artificial Analysis, read October 22, 2026)
- LiveCodeBench (Artificial Analysis run): 1.9% (source: Artificial Analysis, read October 22, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 0.0% (source: Artificial Analysis, read October 22, 2026)
- IFBench: 22.8% (source: Artificial Analysis, read October 22, 2026)
- Long context reasoning (AA-LCR): 6.7% (source: Artificial Analysis, read October 22, 2026)
- τ²-Bench Telecom: 0.0% (source: Artificial Analysis, read October 22, 2026)
- AIME 2025 (Artificial Analysis run): 0.0% (source: Artificial Analysis, read October 22, 2026)
- BALROG: 6.6% (source: Epoch AI benchmarking hub, read October 22, 2026)
- GPQA Diamond (Epoch AI run): 23.9% (source: Epoch AI benchmarking hub, read October 22, 2026)
- OTIS Mock AIME: 0.6% (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMArena Text: 1055 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: coding: 1070 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts: 1044 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: math: 1086 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: instruction following: 1031 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: creative writing: 1033 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: English: 1117 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: non-English: 973 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Chinese: 959 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: German: 1014 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Russian: 941 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: multi-turn: 1030 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: longer queries: 1050 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: expert: 1007 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts in English: 1087 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: software and IT: 1056 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: mathematical work: 1098 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: science: 1055 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: medicine and healthcare: 1009 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: legal and government: 1071 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: business and finance: 1000 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: writing and language: 1030 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: entertainment and media: 1025 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- Berkeley Function Calling Leaderboard (BFCL): 10.8% (source: Berkeley Function Calling Leaderboard, read October 22, 2026)