priorsBuilder

Alibaba · released 2026-04-22

Qwen 3.6 27B

Measured on 38 benchmarks across 2 reasoning efforts.

General frontier

23.7

#99 of 136 models

includes estimates: 24% of the mix is measured for this model

Reasoning efforts in your mix

default23.7#259 of 313
none15.3#296 of 313

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #189default of 58723.1%
  2. #244none of 58715.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #238default of 526-20.0
  2. #396none of 526-53.2

Leader: Opus 5.5 · 46.4

All 38 benchmarks

show 36 more

agentic

AA-Briefcase v1.1

224 results
  1. #149default of 224816

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #147default of 21911.0%

Leader: Gemini 4 · 77.5%

agentic

τ²-Bench Telecom

393 results
  1. #35default of 39394.2%
  2. #41none of 39393.6%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #111default of 20616.7%
  2. #151none of 2069.3%

Leader: Qwen 3.8 Max · 51.3%

coding

SciCode

226 results
  1. #153default of 22642.8%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #60max of 8570.0%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #25max of 6344.9%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #85default of 38734.8%
  2. #159none of 38721.2%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #98default of 23860.7%
  2. #118none of 23851.3%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #160default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench v1.1

105 results
  1. #85max of 10511.9%

Leader: Sonnet 5.5 · 92.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #210default of 61021.4
  2. #230none of 61019.8

Leader: Opus 5.5 · 57.6

cost

AA Intelligence Index Cost per Task

177 results
  1. #97default of 177$0.62

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #103default of 177$1,145

Leader: GPT-6 Luna · $10.63

economics

CorpFin (Vals)

117 results
  1. #49max of 11762.3%

Leader: Opus 5 · 73.2%

economics

GDP.pdf

210 results
  1. #123default of 21011.0%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #164default of 288985
  2. #167none of 288964

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #18max of 8468.3%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #74max of 12571.3%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #84default of 39967.6%
  2. #200none of 39945.7%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #301default of 52619.6%
  2. #360none of 52616.7%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #108default of 52650.7%
  2. #320none of 52616.0%

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

knowledge

CaseLaw (Vals)

53 results
  1. #41max of 5353.2%

Leader: Grok 4.3 · 79.3%

knowledge

GPQA Diamond

539 results
  1. #147default of 53984.2%
  2. #162none of 53982.9%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #104default of 26574.6%
  2. #132none of 26571.7%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #132default of 52377.3%
  2. #238none of 52366.7%

Leader: Kimi K3 · 88.7%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #63max of 11535.1%
  2. #66none of 11534.0%

Leader: GPT-6.1 Sol · 93.7%

reasoning

CritPt

529 results
  1. #218default of 5291.1%
  2. #235none of 5290.9%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Roboflow Visual Reasoning

102 results
  1. #65low of 10259.2%
  2. #74high of 10254.3%

Leader: GPT-6 Astra · 91.2%

reasoning

SAGE

80 results
  1. #40max of 8045.6%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

171 results
  1. #111max of 1712.4%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #155max of 18197.5%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #217none of 3513.6s
  2. #218default of 3513.6s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #274default of 35156.8
  2. #276none of 35156.4

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #59max of 1770.9s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #122max of 17649.0

Leader: Muse Spark 1.1 · 204.3