Skip to content
aiqbench

Meta · model passport

Llama 3 70b Instruct

llama-3-70b-instruct
  • Open weights
  • Llama 3 Community licence
  • Released 2024-04-18(curated)
4/27axes covered
Overall · LMArena
1,277#285 of 396
Best percentile
28.3Overall
Cohort standing
37.3median 32.8

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: 1.2 percentile points between its best and worst axis — 28.3 pct on Overall versus 27.1 pct on Coding.

  • Overall28.3 pct1,277Verify →
  • Instruction following28 pct1,259Verify →
  • Hard prompts27.8 pct1,280Verify →
  • Coding27.1 pct1,306Verify →
  • 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-3-70b-instruct stands at 37.3 (raw mean 27.8) — measured on 4 of 27 axes.

    standingtemplateVerify →

  • llama-3-70b-instruct stands at 37.3 versus a cohort median of 32.8 across 118 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 →