Skip to content
aiqbench

Moonshot · model passport

Kimi K2 5 Instant

kimi-k2-5-instant
  • Open weights
  • Modified MIT licence
  • Released 2026-10-09(first seen on LMArena)
7/27axes covered
Overall · LMArena
1,431#102 of 396
Best percentile
84.4Coding
Cohort standing
60.7median 60.6

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: 46 percentile points between its best and worst axis — 84.4 pct on Coding versus 38.4 pct on Factuality Arena.

  • Coding84.4 pct1,504Verify →
  • Instruction following79.3 pct1,432Verify →
  • Hard prompts77.8 pct1,460Verify →
  • Overall74.5 pct1,431Verify →
  • Vision Arena61.3 pct1,236Verify →
  • WebDev Arena41 pct1,405Verify →
  • Factuality Arena38.4 pct1,429Verify →
  • 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.

  • kimi-k2.5-instant stands at 60.7 (raw mean 65.2) — measured on 7 of 27 axes.

    standingtemplateVerify →

  • kimi-k2.5-instant stands at 60.7 versus a cohort median of 60.6 across 171 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 →