priorsBuilder

Alibaba · released 2026-04-14

Qwen 3.6 35B-A3B

Measured on 32 benchmarks across 2 reasoning efforts.

General frontier

23.2

#101 of 136 models

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

Reasoning efforts in your mix

default23.2#262 of 313
none13.8#300 of 313

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #194default of 58722.2%
  2. #255none of 58713.9%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #243default of 526-22.2
  2. #440none of 526-60.0

Leader: Opus 5.5 · 46.4

All 32 benchmarks

show 30 more

agentic

AA-Briefcase v1.1

224 results
  1. #162default of 224713

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #158default of 2195.2%

Leader: Gemini 4 · 77.5%

agentic

Terminal-Bench 2.0

40 results
  1. #34max of 4024.6%

Leader: GPT-5.5 · 84.7%

agentic

τ²-Bench Telecom

393 results
  1. #25default of 39395.3%
  2. #96none of 39385.1%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #152default of 2069.3%
  2. #180none of 2065.4%

Leader: Qwen 3.8 Max · 51.3%

coding

SciCode

226 results
  1. #188default of 22636.6%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench Hard-AA

387 results
  1. #86default of 38734.8%
  2. #138none of 38725.8%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #129default of 23844.9%
  2. #137none of 23841.6%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #167default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

coding

WeirdML v2

127 results
  1. #107max of 12734.5%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #249default of 61018.2
  2. #282none of 61015.2

Leader: Opus 5.5 · 57.6

cost

AA Intelligence Index Cost per Task

177 results
  1. #86default of 177$0.48

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #90default of 177$896

Leader: GPT-6 Luna · $10.63

economics

GDP.pdf

210 results
  1. #145default of 2106.6%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #176default of 288892
  2. #180none of 288847

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #110default of 39964.4%
  2. #292none of 39936.2%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #315default of 52618.8%
  2. #361none of 52616.7%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #113default of 52649.5%
  2. #451none of 5267.9%

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

knowledge

GPQA Diamond

539 results
  1. #150default of 53984.1%
  2. #177none of 53981.7%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #100default of 26575.0%
  2. #136none of 26571.0%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #197default of 52371.7%
  2. #250none of 52364.3%

Leader: Kimi K3 · 88.7%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #84none of 11520.4%
  2. #95max of 11517.5%

Leader: GPT-6.1 Sol · 93.7%

reasoning

CritPt

529 results
  1. #273default of 5290.3%
  2. #331none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Roboflow Visual Reasoning

102 results
  1. #73low of 10254.8%

Leader: GPT-6 Astra · 91.2%

reliability

Tool-call error rate

171 results
  1. #79max of 1711.1%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #132max of 18198.5%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #154none of 3512.0s
  2. #156default of 3512.0s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #101none of 351141.1
  2. #106default of 351132.6

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #43max of 1770.8s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #65max of 17675.0

Leader: Muse Spark 1.1 · 204.3