priorsBuilder

Moonshot · released 2026-06-12

Kimi K2.7 Code

Measured on 47 benchmarks.

General frontier

30.1

#32 of 32 models

Your mix’s benchmarks

5 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #118default of 58735.0%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #188default of 526-10.2

Leader: Opus 5.5 · 46.4

coding

DeepSWE v1.1

70 results
  1. #63default of 7030.5%

Leader: GPT-6 Astra · 74.1%

math

FrontierMath Tier 4 (v2)

70 results
  1. #56default of 7012.2%

Leader: GPT-6.1 Sol · 100.0%

reasoning

SimpleBench

97 results
  1. #42default of 9757.9%

Leader: Opus 5.5 · 88.4%

All 47 benchmarks

show 42 more

agentic

AA-Briefcase v1.1

224 results
  1. #144default of 224859

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench (Zapier)

115 results
  1. #102default of 1153.2%

Leader: Gemini 4 · 51.3%

agentic

AutomationBench-AA

219 results
  1. #122default of 21924.5%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #29default of 5040.2%

Leader: Fable 5 · 51.1%

agentic

SkillsBench

34 results
  1. #22default of 3450.0%

Leader: DeepSeek V4.1 Flash · 69.8%

agentic

Vending-Bench 2

67 results
  1. #31default of 67$5,083

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #65default of 39390.1%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #99default of 20620.2%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #38default of 581513

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #62default of 1221473

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #48default of 7725.4%

Leader: Sonnet 5.5 · 69.8%

coding

LiveCodeBench (Vals)

127 results
  1. #58default of 12782.0%

Leader: Fable 5.1 · 90.5%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #49default of 620.5%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #50default of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #42default of 6249.4%

Leader: Opus 5.5 · 87.0%

coding

SciCode

226 results
  1. #123default of 22647.8%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #31default of 8578.2%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #36default of 7467.0%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Hard-AA

387 results
  1. #36default of 38744.7%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #78default of 23867.4%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #127default of 2161.0%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench v1.1

105 results
  1. #56default of 10547.2%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #54default of 12754.1%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #153default of 61025.8

Leader: Opus 5.5 · 57.6

cost

AA Intelligence Index Cost per Task

177 results
  1. #93default of 177$0.54

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #93default of 177$993

Leader: GPT-6 Luna · $10.63

economics

GDP.pdf

210 results
  1. #118default of 21011.2%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #151default of 2881037

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #114default of 39963.1%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #125default of 52639.6%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #306default of 52617.6%

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

knowledge

GPQA Diamond

539 results
  1. #73default of 53989.6%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #100default of 52379.3%

Leader: Kimi K3 · 88.7%

long-context

MLCR-AA

94 results
  1. #45default of 9416.1%

Leader: Sonnet 5.5 · 75.0%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #46default of 11554.0%

Leader: GPT-6.1 Sol · 93.7%

reasoning

CritPt

529 results
  1. #115default of 52910.0%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #76default of 1711.1%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #110default of 18199.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #194default of 3512.8s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #218default of 35174.8

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #111default of 1771.6s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #128default of 17647.0

Leader: Muse Spark 1.1 · 204.3