Skip to content
aiqbench

Meta · model passport

Llama 3 1 405b Instruct Bf16

llama-3-1-405b-instruct-bf16
  • Open weights
  • Llama 3.1 Community licence
  • Released 2024-07-23(curated)
4/27axes covered
Overall · LMArena
1,335#222 of 396
Best percentile
44.2Overall
Cohort standing
46.4median 36.3

What the data says

Benchmarked on 4 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 1.5 percentile points between its best and worst axis — 44.2 pct on Overall versus 42.7 pct on Instruction following.

  • Overall44.2 pct1,335Verify →
  • Coding44.2 pct1,376Verify →
  • Hard prompts43.9 pct1,342Verify →
  • Instruction following42.7 pct1,314Verify →
  • 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

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.

  • llama-3.1-405b-instruct-bf16 stands at 46.4 (raw mean 43.8) — measured on 4 of 27 axes.

    standingtemplateVerify →

  • llama-3.1-405b-instruct-bf16 stands at 46.4 versus a cohort median of 36.3 across 131 models released within 180 days — above 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 →