Skip to content
aiqbench

Model passport

Alpaca 13b

alpaca-13b
  • Open weights
  • Non-commercial licence
  • Released 2023-03-13(curated)
4/27axes covered
Overall · LMArena
1,070#385 of 396
Best percentile
3.0Overall
Cohort standing
22.6median 25.6

What the data says

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

Weakest axes

  • 1 pct — Coding (999)
  • 1.5 pct — Hard prompts (1,010)
  • 2.5 pct — Instruction following (1,025)

Uneven: 2 percentile points between its best and worst axis — 3 pct on Overall versus 1 pct on Coding.

  • Overall3 pct1,070Verify →
  • Instruction following2.5 pct1,025Verify →
  • Hard prompts1.5 pct1,010Verify →
  • Coding1 pct999Verify →
  • 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.

  • alpaca-13b stands at 22.6 (raw mean 2) — measured on 4 of 27 axes.

    standingtemplateVerify →

  • alpaca-13b stands at 22.6 versus a cohort median of 25.6 across 27 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 →