Skip to content
aiqbench

Moonshot · model passport

Kimi K2 Thinking Turbo

kimi-k2-thinking-turbo
  • Open weights
  • Modified MIT licence
  • Released 2025-11-06(curated)
8/27axes covered
Overall · LMArena
1,430#104 of 396
Best percentile
76.7Coding
Cohort standing
57.2median 53.6

What the data says

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

Uneven: 58 percentile points between its best and worst axis — 76.7 pct on Coding versus 18.7 pct on WebDev Arena.

  • Coding76.7 pct1,487Verify →
  • Hard prompts75.5 pct1,453Verify →
  • Instruction following74.5 pct1,418Verify →
  • Overall74 pct1,430Verify →
  • GPQA Diamond67 pct84.2%Verify →
  • AIME (math)59 pct83.1%Verify →
  • Factuality Arena33.7 pct1,423Verify →
  • WebDev Arena18.7 pct1,322Verify →
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot 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-thinking-turbo stands at 57.2 (raw mean 59.9) — measured on 8 of 27 axes.

    standingtemplateVerify →

  • kimi-k2-thinking-turbo stands at 57.2 versus a cohort median of 53.6 across 132 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 →