priorsBuilder

Moonshot · released 2026-01-27

Kimi K2.5

Measured on 67 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

4 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #142default of 58730.7%
  2. #265none of 58713.2%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #169default of 526-7.3
  2. #210none of 526-13.8

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #70none of 19652.0%
  2. #120high of 19631.0%

Leader: Opus 4.8 · 95.0%

reasoning

SimpleBench

97 results
  1. #56high of 9746.8%

Leader: Opus 5.5 · 88.4%

All 67 benchmarks

show 63 more

agentic

APEX-Agents-AA

33 results
  1. #28default of 3311.5%

Leader: Gemini 3.5 Flash · 47.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #78high of 790.0%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #59high of 7815.9%

Leader: Muse Spark 1.3 · 55.3%

agentic

OSWorld-Verified

13 results
  1. #8high of 1363.3%

Leader: Fable 5 · 86.0%

agentic

Terminal-Bench 2.0

40 results
  1. #21high of 4043.2%

Leader: GPT-5.5 · 84.7%

agentic

Vending-Bench 2

67 results
  1. #52high of 67$1,198

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #17default of 39395.9%
  2. #118none of 39381.3%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #124default of 20614.2%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #50high of 581440

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #71high of 1221436

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #66high of 777.0%

Leader: Sonnet 5.5 · 69.8%

coding

FrontierSWE v1

17 results
  1. #15high of 1723.3%

Leader: Fable 5 · 88.2%

coding

LiveCodeBench (Vals)

127 results
  1. #46high of 12783.9%

Leader: Fable 5.1 · 90.5%

coding

SWE Atlas-QnA

22 results
  1. #20high of 2213.1%

Leader: Opus 5 · 63.2%

coding

SWE-bench Verified (Vals)

85 results
  1. #58high of 8570.0%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #32high of 6340.4%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #66high of 7441.9%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Hard-AA

387 results
  1. #83default of 38734.8%
  2. #167none of 38718.9%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #127default of 23845.7%

Leader: Fable 5.1 · 91.4%

coding

Vibe Code Bench v1.1

105 results
  1. #79high of 10517.5%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #74high of 12745.6%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #183default of 61023.5
  2. #234none of 61019.4

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #68high of 2201450

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #72high of 2201452

Leader: Gemini 4 · 1553

composite

Vals RSI Index v1.1

24 results
  1. #24high of 246.8%

Leader: Opus 5.5 · 37.3%

composite

Vals RSI Index v1.1: Harness Engineering: Judge

24 results
  1. #24high of 242.1%

Leader: GPT-6 Sol · 22.8%

composite

Vals RSI Index v1.1: Post-training: Finance Agent

24 results
  1. #7high of 240.0%

Leader: Opus 5.5 · 35.1%

composite

Vals RSI Index v1.1: Pre-training: Compression

24 results
  1. #24high of 240.0%

Leader: Opus 5.5 · 46.5%

composite

Vals RSI Index v1.1: Pre-training: LM Training

24 results
  1. #23high of 2425.3%

Leader: Opus 5.5 · 53.0%

creative

MineBench

72 results
  1. #54high of 721234

Leader: GPT-6 Astra Pro · 2281

economics

CorpFin (Vals)

117 results
  1. #10high of 11768.3%

Leader: Opus 5 · 73.2%

economics

Excel Modeling Benchmark

74 results
  1. #64high of 7428.5%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #67high of 7835.8%

Leader: Gemini 4 · 65.4%

economics

GDPval-AA v2.1

288 results
  1. #181default of 288839

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #31high of 8466.5%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #39high of 12574.2%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #68default of 39970.2%
  2. #219none of 39943.7%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #149default of 52635.2%
  2. #240none of 52624.1%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #110none of 52650.0%
  2. #187default of 52634.3%

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

knowledge

CaseLaw (Vals)

53 results
  1. #28high of 5358.7%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #44none of 11884.0%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #94default of 53987.9%
  2. #203none of 53978.9%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #55high of 12284.1%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #62high of 9439.3%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #17high of 8094.4%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #67high of 9676.4%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #51high of 12285.9%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #26high of 8184.3%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #97default of 26575.4%
  2. #124none of 26573.1%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #122default of 52378.0%
  2. #234none of 52367.3%

Leader: Kimi K3 · 88.7%

long-context

Arena Document

43 results
  1. #33high of 431430

Leader: Opus 5 · 1516

math

AIME (Vals)

82 results
  1. #11high of 8295.6%

Leader: Gemini 3.1 Pro · 98.1%

other

Arena Vision

116 results
  1. #49high of 1161252

Leader: Fable 5 · 1308

reasoning

ARC-AGI-1

215 results
  1. #132high of 21565.3%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #137high of 21611.8%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #173default of 5293.1%
  2. #250none of 5290.6%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

SAGE

80 results
  1. #19high of 8049.9%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

172 results
  1. #112high of 1722.5%

Leader: Gemini 4 · 0.0%

reliability

Uptime (7d)

182 results
  1. #144high of 18298.2%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #118default of 3511.6s
  2. #160none of 3512.1s

Leader: Gemini 2.5 Flash Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #263default of 35160.6
  2. #264none of 35159.9

Leader: Celeris-1 · 1564.1

speed

Provider latency

178 results
  1. #77high of 1781.1s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #133high of 17646.0

Leader: Muse Spark 1.1 · 204.5