Skip to content
aiqbench

xAI · model passport

Grok 2

grok-2
  • Cloud only
  • Proprietary licence
  • Released 2024-08-14(curated)
7/27axes covered
Overall · LMArena
1,336#220 of 396
Best percentile
44.7Overall
Cohort standing
42.6median 37.3

What the data says

Benchmarked on 7 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 11.9 percentile points between its best and worst axis — 44.7 pct on Overall versus 32.8 pct on LiveCodeBench (Artificial Analysis).

  • Overall44.7 pct1,336Verify →
  • MMLU-Pro (Artificial Analysis)43.1 pct70.9%Verify →
  • Instruction following41.4 pct1,312Verify →
  • Hard prompts39.1 pct1,326Verify →
  • Coding38.6 pct1,358Verify →
  • LiveBench36.4 pct46.5%Verify →
  • LiveCodeBench (Artificial Analysis)32.8 pct26.7%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
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot 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.

  • grok-2-2024-08-13 stands at 42.6 (raw mean 39.5) — measured on 7 of 27 axes.

    standingtemplateVerify →

  • grok-2-2024-08-13 stands at 42.6 versus a cohort median of 37.3 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 →