priorsBuilder

Moonshot · released 2025-07-11

Kimi K2

Measured on 44 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. #184default of 58723.8%
  2. #351none of 5877.4%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #240default of 526-21.4
  2. #258none of 526-26.6

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #176medium of 19610.0%

Leader: Opus 4.8 · 95.0%

reasoning

SimpleBench

97 results
  1. #68medium of 9739.6%

Leader: Opus 5.5 · 88.4%

All 44 benchmarks

show 40 more

agentic

Terminal-Bench 2.0

40 results
  1. #26medium of 4035.7%

Leader: GPT-5.5 · 84.7%

agentic

τ²-Bench Telecom

393 results
  1. #47default of 39393.0%
  2. #148none of 39373.4%

Leader: GLM 5.2 · 99.1%

coding

Arena WebDev

122 results
  1. #106medium of 1221322

Leader: Opus 5.5 · 1813

coding

LiveCodeBench

282 results
  1. #13default of 28285.3%
  2. #101none of 28261.0%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #86medium of 12770.4%

Leader: Fable 5.1 · 90.5%

coding

SWE-bench Verified (Vals)

85 results
  1. #75medium of 8560.2%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #39medium of 6337.1%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #108default of 38731.1%
  2. #149none of 38723.5%

Leader: GPT-5.6 Sol · 65.9%

coding

WeirdML v2

127 results
  1. #80medium of 12742.8%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #201default of 61022.0
  2. #280none of 61015.3

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #94medium of 2201430

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #93medium of 2201433

Leader: Gemini 4 · 1553

creative

MineBench

72 results
  1. #65medium of 721009

Leader: GPT-6 Astra Pro · 2281

economics

CorpFin (Vals)

117 results
  1. #67medium of 11760.6%

Leader: Opus 5 · 73.2%

economics

TaxEval (Vals)

125 results
  1. #71medium of 12571.7%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #81default of 39968.1%
  2. #242none of 39941.7%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #171default of 52630.9%
  2. #200none of 52627.4%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #216none of 52630.3%
  2. #243default of 52624.4%

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

knowledge

CaseLaw (Vals)

53 results
  1. #11medium of 5365.7%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #67none of 11880.8%
  2. #94default of 11873.5%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #154default of 53983.8%
  2. #227none of 53976.7%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #74medium of 12278.5%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedQA (Vals)

80 results
  1. #27medium of 8092.6%

Leader: o1 · 96.5%

knowledge

MMLU Pro (Vals)

122 results
  1. #80medium of 12281.1%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #32default of 28584.8%
  2. #58none of 28582.4%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #191default of 52372.0%
  2. #296none of 52353.0%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #36medium of 8285.4%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #10default of 22894.7%
  2. #107none of 22857.3%

Leader: GPT-5.2 · 99.0%

math

MATH 500 (Vals)

48 results
  1. #13medium of 4894.2%

Leader: Gemini 3 Pro · 96.4%

math

MATH-500

162 results
  1. #23none of 16297.1%

Leader: GPT-5 · 99.4%

math

MGSM (Vals)

62 results
  1. #26medium of 6290.9%

Leader: Opus 4.5 · 95.2%

other

Poker Agent

17 results
  1. #14medium of 171012

Leader: GPT-5.2 · 1132

reasoning

CritPt

529 results
  1. #184default of 5292.6%
  2. #329none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #77medium of 13581.5%

Leader: Fable 5 · 88.6%

reliability

Tool-call error rate

172 results
  1. #100medium of 1721.8%

Leader: Gemini 4 · 0.0%

reliability

Uptime (7d)

182 results
  1. #15medium of 182100.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #97default of 3511.2s
  2. #123none of 3511.6s

Leader: Gemini 2.5 Flash Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #82default of 351160.2
  2. #269none of 35158.4

Leader: Celeris-1 · 1564.1

speed

Provider latency

178 results
  1. #76medium of 1781.1s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #139medium of 17642.0

Leader: Muse Spark 1.1 · 204.5