priorsBuilder

Moonshot · released 2026-04-20

Kimi K2.6

Measured on 78 benchmarks.

General frontier

31.6

#31 of 32 models · best at none

Your mix’s benchmarks

4 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #101default of 58737.5%
  2. #211none of 58719.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #103default of 5265.3
  2. #181none of 526-9.2

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #37none of 19665.0%
  2. #72xhigh of 19650.0%

Leader: Opus 4.8 · 95.0%

math

FrontierMath Tier 4 (v2)

70 results
  1. #43xhigh of 7025.6%

Leader: GPT-6.1 Sol · 100.0%

All 78 benchmarks

show 74 more

agentic

AA-Briefcase v1.1

224 results
  1. #148default of 224820

Leader: Sonnet 5.5 · 1823

agentic

APEX-Agents-AA

33 results
  1. #13default of 3328.5%

Leader: Gemini 3.5 Flash · 47.1%

agentic

AutomationBench (Zapier)

115 results
  1. #104xhigh of 1152.6%

Leader: Gemini 4 · 51.3%

agentic

AutomationBench-AA

219 results
  1. #142default of 21913.0%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #31default of 5038.5%

Leader: Fable 5 · 51.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #51xhigh of 791.7%

Leader: Muse Spark 1.2 · 25.4%

agentic

ITBench-AA

45 results
  1. #32default of 4531.2%

Leader: GPT-5.6 Sol · 56.2%

agentic

Legal Research Bench

78 results
  1. #60xhigh of 7815.9%

Leader: Muse Spark 1.3 · 55.3%

agentic

OSWorld-Verified

13 results
  1. #6xhigh of 1373.1%

Leader: Fable 5 · 86.0%

agentic

Tax Agent Bench

69 results
  1. #52xhigh of 6912.4%

Leader: Fable 5.1 · 49.2%

agentic

Vending-Bench 2

67 results
  1. #19xhigh of 67$6,205

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #16default of 39395.9%
  2. #39none of 39393.9%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #88default of 20623.3%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #35xhigh of 581521

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #52xhigh of 1221509

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #43xhigh of 7727.8%

Leader: Sonnet 5.5 · 69.8%

coding

DeepSWE v1

29 results
  1. #18xhigh of 2923.9%

Leader: GPT-5.5 · 70.0%

coding

FrontierSWE v1

17 results
  1. #16xhigh of 1722.2%

Leader: Fable 5 · 88.2%

coding

LiveCodeBench (Vals)

127 results
  1. #20xhigh of 12786.8%

Leader: Fable 5.1 · 90.5%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #48xhigh of 620.5%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #49xhigh of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #44xhigh of 6248.0%

Leader: Opus 5.5 · 87.0%

coding

SciCode

226 results
  1. #93default of 22651.5%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #39xhigh of 8576.2%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #13xhigh of 6357.3%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #52xhigh of 7453.6%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Hard-AA

387 results
  1. #40default of 38743.9%
  2. #65none of 38737.9%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #79default of 23865.9%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #136default of 2160.5%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench v1.1

105 results
  1. #60xhigh of 10537.9%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #52xhigh of 12755.9%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #143default of 61027.0
  2. #181none of 61023.6

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #53xhigh of 2201461

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #65xhigh of 2201461

Leader: Gemini 4 · 1553

composite

Vals Multimodal Index v1.2

33 results
  1. #19xhigh of 3356.4%

Leader: Fable 5 · 74.2%

cost

AA Intelligence Index Cost per Task

177 results
  1. #103default of 177$0.80

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #119default of 177$1,528

Leader: GPT-6 Luna · $10.63

creative

MineBench

72 results
  1. #40xhigh of 721475

Leader: GPT-6 Astra Pro · 2281

economics

CorpFin (Vals)

117 results
  1. #17xhigh of 11766.7%

Leader: Opus 5 · 73.2%

economics

Excel Modeling Benchmark

74 results
  1. #38xhigh of 7457.9%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #54xhigh of 7844.9%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #104default of 21013.0%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #150default of 2881038

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #36xhigh of 8465.8%

Leader: Opus 5 · 72.1%

economics

Public Benefits Bench v1 (Vals)

13 results
  1. #9xhigh of 1353.4%

Leader: Fable 5 · 71.7%

economics

TaxEval (Vals)

125 results
  1. #33xhigh of 12574.7%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #23default of 39976.0%
  2. #214none of 39944.3%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #164default of 52632.6%
  2. #237none of 52624.3%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #77default of 52659.5%
  2. #88none of 52655.8%

Leader: MiniCPM5-1B (Non-reasoning) · 99.1%

knowledge

CaseLaw (Vals)

53 results
  1. #22xhigh of 5361.2%

Leader: Grok 4.3 · 79.3%

knowledge

GPQA Diamond

539 results
  1. #52default of 53991.1%
  2. #204none of 53978.8%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #31xhigh of 12289.1%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #61xhigh of 9440.1%

Leader: Opus 5 · 63.6%

knowledge

MedScribe

96 results
  1. #60xhigh of 9678.1%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #25xhigh of 12287.6%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #21xhigh of 8186.3%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #58default of 26579.4%

Leader: Opus 5.5 · 87.7%

knowledge

Public Benefits Bench v1.1

50 results
  1. #39xhigh of 5056.6%

Leader: Opus 5 · 76.9%

long-context

AA-LCR v1.1

523 results
  1. #61default of 52381.0%
  2. #216none of 52369.7%

Leader: Kimi K3 · 88.7%

long-context

Arena Document

43 results
  1. #27xhigh of 431451

Leader: Opus 5 · 1516

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #41xhigh of 11557.2%

Leader: GPT-6.1 Sol · 93.7%

other

Arena Vision

116 results
  1. #40xhigh of 1161265

Leader: Fable 5 · 1308

reasoning

Blueprint-Bench 2

28 results
  1. #28xhigh of 283.9%

Leader: Gemini 4 · 54.4%

reasoning

CritPt

529 results
  1. #132default of 5298.0%
  2. #205none of 5291.4%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Furniture Assembly

31 results
  1. #29xhigh of 3121.7%

Leader: Opus 5.5 · 83.3%

reasoning

LegalBench

135 results
  1. #29xhigh of 13584.7%

Leader: Fable 5 · 88.6%

reasoning

Roboflow Visual Reasoning

102 results
  1. #66high of 10258.9%
  2. #91low of 10239.1%

Leader: GPT-6 Astra · 91.2%

reasoning

SAGE

80 results
  1. #17xhigh of 8050.2%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

172 results
  1. #75xhigh of 1721.0%

Leader: Gemini 4 · 0.0%

reliability

Uptime (7d)

182 results
  1. #150xhigh of 18298.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #195none of 3512.8s
  2. #199default of 3512.9s

Leader: Gemini 2.5 Flash Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #314default of 35143.4
  2. #321none of 35141.3

Leader: Celeris-1 · 1564.1

speed

Provider latency

178 results
  1. #88xhigh of 1781.3s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #148xhigh of 17635.5

Leader: Muse Spark 1.1 · 204.5