Skip to content
aiqbench

xAI · model passport

Grok 3 Mini

grok-3-mini
  • Cloud only
  • Proprietary licence
  • Released 2025-02-19(curated)
5/27axes covered
Overall · LMArena
1,364#188 of 396
Best percentile
54.8Instruction following
Cohort standing
46.6median 44.4

What the data says

Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 13.5 pct — ARC-AGI-2 (0.4%)

Uneven: 41.3 percentile points between its best and worst axis — 54.8 pct on Instruction following versus 13.5 pct on ARC-AGI-2.

  • Instruction following54.8 pct1,361Verify →
  • Overall52.8 pct1,364Verify →
  • Hard prompts52.3 pct1,378Verify →
  • Coding49.4 pct1,392Verify →
  • ARC-AGI-213.5 pct0.4%Verify →
  • 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
  • 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.

  • grok-3-mini-high stands at 46.6 (raw mean 44.5) — measured on 5 of 27 axes.

    standingtemplateVerify →

  • grok-3-mini-high stands at 46.6 versus a cohort median of 44.4 across 146 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 →