Skip to content
aiqbench

Meta AI · model passport

Meta: Llama 3.3 70B Instruct

llama-3-3-70b-instruct
  • Open weights
  • Llama-3.3 licence
  • 70.6B params
  • 131,072 context
  • Released 2024-12-06(curated)
8/27axes covered
Overall · LMArena
1,318#244 of 396
Best percentile
46.3BFCL v4 (function calling)
Cohort standing
36.2median 41.9

What the data says

Benchmarked on 8 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 8 pct — SimpleBench (19.9%)

Uneven: 38.3 percentile points between its best and worst axis — 46.3 pct on BFCL v4 (function calling) versus 8 pct on SimpleBench.

  • BFCL v4 (function calling)Dormant board46.3 pct31.9%Verify →
  • Overall38.6 pct1,318Verify →
  • Hard prompts37.6 pct1,321Verify →
  • Instruction following36.4 pct1,293Verify →
  • Coding34.5 pct1,346Verify →
  • GPQA Diamond30.3 pct47.4%Verify →
  • AIME (math)16.5 pct5.1%Verify →
  • SimpleBench8 pct19.9%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
  • 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-3.3-70B-Instruct
Parameters70.6B
ArchitectureLlamaForCausalLM
LicenceLlama-3.3
AccessGated — you must accept the repo's terms before downloading

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "meta-llama/Llama-3.3-70B-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-3.3-70b-instruct
Context length131,072 tokens
Max output16,384 tokens
Input price$0.10 per 1M tokens
Output price$0.32 per 1M tokens

API parameters this endpoint supports

Frequency penaltyLogit biasLogprobsMax tokensMin-pPresence penaltyRepetition penaltyResponse formatSeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop-kTop logprobsTop-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-3.3-70b-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-3.3-70b-instruct stands at 36.2 (raw mean 31) — measured on 8 of 27 axes.

    standingtemplateVerify →

  • llama-3.3-70b-instruct stands at 36.2 versus a cohort median of 41.9 across 137 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 →