Skip to content
aiqbench

Prime-Intellect · model passport

Intellect 3

intellect-3
  • Open weights
  • MIT licence
  • Released 2026-10-15(first seen on LMArena)
8/27axes covered
Overall · LMArena
1,356#195 of 396
Best percentile
87.4LiveCodeBench (Artificial Analysis)
Cohort standing
50.7median 60.8

What the data says

Benchmarked on 8 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 87.4 pct — LiveCodeBench (Artificial Analysis) (77.7%)

Weakest axes

  • 10.5 pct — Factuality Arena (1,373)

Uneven: 76.9 percentile points between its best and worst axis — 87.4 pct on LiveCodeBench (Artificial Analysis) versus 10.5 pct on Factuality Arena.

  • LiveCodeBench (Artificial Analysis)87.4 pct77.7%Verify →
  • MMLU-Pro (Artificial Analysis)79.4 pct82.2%Verify →
  • Coding53.5 pct1,415Verify →
  • Hard prompts51.8 pct1,375Verify →
  • Overall51 pct1,356Verify →
  • Instruction following48.7 pct1,332Verify →
  • IFBench (Artificial Analysis)25.6 pct34.0%Verify →
  • Factuality Arena10.5 pct1,373Verify →
  • WebDev ArenaNot benchmarked
  • Vision 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
  • 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.

  • intellect-3 stands at 50.7 (raw mean 51) — measured on 8 of 27 axes.

    standingtemplateVerify →

  • intellect-3 stands at 50.7 versus a cohort median of 60.8 across 168 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 →