Skip to content
aiqbench

Meta · model passport

Codellama 70b Instruct

codellama-70b-instruct
  • Open weights
  • Llama 2 Community licence
  • 69.0B params
  • Released 2024-01-29(curated)
3/27axes covered
Overall · LMArena
1,119#374 of 396
Best percentile
11.1Hard prompts
Cohort standing
28.8median 30.0

What the data says

Benchmarked on 3 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 5.8 pct — Overall (1,119)
  • 6.1 pct — Instruction following (1,098)
  • 11.1 pct — Hard prompts (1,160)

Uneven: 5.3 percentile points between its best and worst axis — 11.1 pct on Hard prompts versus 5.8 pct on Overall.

  • Hard prompts11.1 pct1,160Verify →
  • Instruction following6.1 pct1,098Verify →
  • Overall5.8 pct1,119Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not 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
  • CodingNot 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/CodeLlama-70b-Instruct-hf
Parameters69.0B
ArchitectureLlamaForCausalLM
LicenceLlama 2 Community
AccessGated — you must accept the repo's terms before downloading

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "meta-llama/CodeLlama-70b-Instruct-hf"
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 →

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.

  • codellama-70b-instruct stands at 28.8 (raw mean 7.7) — measured on 3 of 27 axes.

    standingtemplateVerify →

  • codellama-70b-instruct stands at 28.8 versus a cohort median of 30 across 90 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 →