Skip to content
aiqbench

OpenAI · model passport

o1 Mini

o1-mini
  • Cloud only
  • Proprietary licence
  • Released 2024-09-12(curated)
12/27axes covered
Overall · LMArena
1,337#218 of 396
Best percentile
61.5LiveCodeBench (Artificial Analysis)
Cohort standing
41.9median 38.0

What the data says

Benchmarked on 12 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 4.6 pct — SimpleBench (18.1%)

Uneven: 56.9 percentile points between its best and worst axis — 61.5 pct on LiveCodeBench (Artificial Analysis) versus 4.6 pct on SimpleBench.

  • LiveCodeBench (Artificial Analysis)61.5 pct57.6%Verify →
  • LiveBench58.1 pct57.8%Verify →
  • MMLU-Pro (Artificial Analysis)48.7 pct74.2%Verify →
  • Instruction following48.2 pct1,331Verify →
  • Hard prompts47.7 pct1,360Verify →
  • Coding46.5 pct1,386Verify →
  • Overall45.2 pct1,337Verify →
  • GPQA Diamond43.9 pct62.4%Verify →
  • AIME (math)37 pct46.9%Verify →
  • FrontierMath20.3 pct1.7%Verify →
  • ARC-AGI-216.9 pct0.8%Verify →
  • SimpleBench4.6 pct18.1%Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • Humanity's Last ExamNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not 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.

  • o1-mini stands at 41.9 (raw mean 39.9) — measured on 12 of 27 axes.

    standingtemplateVerify →

  • o1-mini stands at 41.9 versus a cohort median of 38 across 129 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 →