priorsBuilder

Thinking Machines · released 2026-07-15

Inkling

Measured on 74 benchmarks across 2 reasoning efforts.

General frontier

34.2

#71 of 136 models · best at max

includes estimates: 15% of the mix is measured for this model

Reasoning efforts in your mix

max34.2#190 of 313
xhigh30.1#221 of 313

Your mix’s benchmarks

4 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #139xhigh of 58731.9%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #118xhigh of 5262.0

Leader: Opus 5.5 · 46.4

math

FrontierMath Tier 4 (v2)

70 results
  1. #60xhigh of 704.9%

Leader: GPT-6.1 Sol · 100.0%

reasoning

SimpleBench

97 results
  1. #53max of 9750.0%

Leader: Opus 5.5 · 88.4%

All 74 benchmarks

show 70 more

agentic

AA-AnalystAgent

44 results
  1. #27xhigh of 4423.8%

Leader: Gemini 3.7 Flash · 60.0%

agentic

AA-Briefcase v1.1

224 results
  1. #147xhigh of 224832

Leader: Sonnet 5.5 · 1823

agentic

Agent Arena

50 results
  1. #49max of 50-11.5%

Leader: Opus 5.5 · 15.5%

agentic

AutomationBench-AA

219 results
  1. #159xhigh of 2195.0%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #33xhigh of 5038.0%

Leader: Fable 5 · 51.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #48max of 792.1%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #49max of 7828.4%

Leader: Muse Spark 1.3 · 55.3%

agentic

SkillsBench

34 results
  1. #33max of 3426.1%

Leader: DeepSeek V4.1 Flash · 69.8%

agentic

Tax Agent Bench

69 results
  1. #50max of 6915.3%

Leader: Fable 5.1 · 49.2%

agentic

Terminal-Bench 4.0 (Vals)

47 results
  1. #44max of 470.5%

Leader: Opus 5.5 · 65.2%

agentic

τ³-Banking

206 results
  1. #71xhigh of 20629.1%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena WebDev

122 results
  1. #78max of 1221413

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #62max of 7711.8%

Leader: Sonnet 5.5 · 69.8%

coding

FrontierCode 1.1 Extended

130 results
  1. #126max of 13024.8%

Leader: Opus 5.5 · 65.3%

coding

FrontierCode 1.1 Main

130 results
  1. #125max of 13014.0%

Leader: Opus 5.5 · 54.6%

coding

FrontierSWE v2

21 results
  1. #21max of 214.1%

Leader: GPT-6 Astra · 65.5%

coding

IOI

44 results
  1. #42max of 4414.9%

Leader: Gemini 4 · 100.0%

coding

LiveCodeBench (Vals)

127 results
  1. #32max of 12785.5%

Leader: Fable 5.1 · 90.5%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #62max of 620.0%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #60max of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #54max of 6224.4%

Leader: Opus 5.5 · 87.0%

coding

SciCode

226 results
  1. #129xhigh of 22647.0%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #33max of 8577.6%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #62max of 7447.6%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Science-AA

46 results
  1. #43xhigh of 460.0%

Leader: GPT-6 Astra · 63.3%

coding

Terminal-Bench v2.1-AA

238 results
  1. #110xhigh of 23855.1%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #130xhigh of 2161.0%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench 1-100

22 results
  1. #21max of 227.3%

Leader: Opus 5.5 · 30.4%

coding

Vibe Code Bench v1.1

105 results
  1. #77max of 10519.2%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #109max of 12732.3%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #162xhigh of 61025.0

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #80max of 2201441

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #88max of 2201441

Leader: Gemini 4 · 1553

composite

Vals Index

47 results
  1. #45max of 4728.7%

Leader: Gemini 4 · 68.9%

composite

Vals Multimodal Index v1.2

33 results
  1. #27max of 3349.4%

Leader: Fable 5 · 74.2%

economics

CorpFin (Vals)

117 results
  1. #7max of 11768.6%

Leader: Opus 5 · 73.2%

economics

Excel Modeling Benchmark

74 results
  1. #59max of 7438.4%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #52max of 7846.6%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #107xhigh of 21012.8%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #142xhigh of 2881076

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #48max of 8464.0%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #20max of 12575.3%

Leader: Muse Spark 1.2 · 80.4%

knowledge

AA-Omniscience Accuracy

526 results
  1. #108xhigh of 52641.5%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #202xhigh of 52632.3%

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

knowledge

GPQA Diamond

539 results
  1. #102xhigh of 53987.2%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #40max of 12287.1%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

Harvey LAB-AA v1.1

27 results
  1. #26xhigh of 270.0%

Leader: Muse Wonder Full (Max) · 13.1%

knowledge

MedCode

94 results
  1. #52max of 9441.2%

Leader: Opus 5 · 63.6%

knowledge

MedScribe

96 results
  1. #26max of 9685.4%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #42max of 12286.3%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #49max of 8178.5%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #118xhigh of 26573.5%

Leader: Opus 5.5 · 87.7%

knowledge

Public Benefits Bench v1.1

50 results
  1. #36max of 5058.5%

Leader: Opus 5 · 76.9%

long-context

AA-LCR v1.1

523 results
  1. #131xhigh of 52377.3%

Leader: Kimi K3 · 88.7%

long-context

MLCR-AA

94 results
  1. #60xhigh of 9412.2%

Leader: Sonnet 5.5 · 75.0%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #68xhigh of 11533.3%

Leader: GPT-6.1 Sol · 93.7%

math

ProofBench v1.1

52 results
  1. #51max of 520.0%

Leader: Sonnet 5.5 · 100.0%

reasoning

ARC-AGI-1

215 results
  1. #106max of 21579.5%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #108max of 21636.5%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #148xhigh of 5295.4%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #63max of 13582.9%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #62max of 8036.6%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

171 results
  1. #151max of 1716.0%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #156max of 18197.5%

Leader: GPT-5 Pro · 100.0%

safety

CyberBench v1.1

45 results
  1. #30max of 4566.8%

Leader: Wonder · 80.4%

safety

SRE Bench

32 results
  1. #32max of 320.0%

Leader: GPT-6 Astra · 56.9%

speed

Latency (Time to First Token)

351 results
  1. #146xhigh of 3511.8s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #56xhigh of 351185.5

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #33max of 1770.7s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #53max of 17681.5

Leader: Muse Spark 1.1 · 204.3