Skip to content
aiqbench

Meta · model passport

Meta: Llama 3.2 1B Instruct

llama-3-2-1b-instruct
  • Open weights
  • Llama 3.2 licence
  • 1.2B params
  • 60,000 context
  • Released 2024-09-25(curated)
7/27axes covered
Overall · LMArena
1,111#378 of 396
Best percentile
5.6Coding
Cohort standing
18.1median 38.3

What the data says

Benchmarked on 7 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 3 pct — AIME (math) (0.6%)
  • 3.6 pct — GPQA Diamond (23.9%)
  • 3.7 pct — BFCL v4 (function calling) (10.8%)

Uneven: 2.6 percentile points between its best and worst axis — 5.6 pct on Coding versus 3 pct on AIME (math).

  • Coding5.6 pct1,149Verify →
  • Hard prompts5.3 pct1,114Verify →
  • Instruction following5.1 pct1,086Verify →
  • Overall4.8 pct1,111Verify →
  • BFCL v4 (function calling)Dormant board3.7 pct10.8%Verify →
  • GPQA Diamond3.6 pct23.9%Verify →
  • AIME (math)3 pct0.6%Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Run it yourself

Repositorymeta-llama/Llama-3.2-1B-Instruct
Parameters1.2B
ArchitectureLlamaForCausalLM
LicenceLlama 3.2
AccessGated — you must accept the repo's terms before downloading

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "meta-llama/Llama-3.2-1B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Use it hosted

API model IDmeta-llama/llama-3.2-1b-instruct
Context length60,000 tokens
Max output54,000 tokens
Input price$0.03 per 1M tokens
Output price$0.20 per 1M tokens

API parameters this endpoint supports

Frequency penaltyLogit biasMax tokensMin-pPresence penaltyRepetition penaltySeedStop sequencesTemperatureTop-kTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"meta-llama/llama-3.2-1b-instruct","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • llama-3.2-1b-instruct stands at 18.1 (raw mean 4.4) — measured on 7 of 27 axes.

    standingtemplateVerify →

  • llama-3.2-1b-instruct stands at 18.1 versus a cohort median of 38.3 across 134 models released within 180 days — below the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →