priorsBuilder

Alibaba · released 2026-02-24

Qwen 3.5 27B

Measured on 27 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #183default of 58723.9%
  2. #253none of 58713.9%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #333default of 526-44.0
  2. #354none of 526-47.7

Leader: Opus 5.5 · 46.4

All 27 benchmarks

show 25 more

agentic

ITBench-AA

45 results
  1. #26default of 4535.5%

Leader: GPT-5.6 Sol · 56.2%

agentic

Vending-Bench 2

67 results
  1. #59high of 67$202

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #40default of 39393.9%
  2. #82none of 39387.1%

Leader: GLM 5.2 · 99.1%

coding

Arena WebDev

122 results
  1. #97high of 1221358

Leader: Opus 5.5 · 1813

coding

Terminal-Bench Hard-AA

387 results
  1. #98default of 38732.6%
  2. #102none of 38731.8%

Leader: GPT-5.6 Sol · 65.9%

coding

WeirdML v2

127 results
  1. #90high of 12739.5%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #189default of 61022.9
  2. #235none of 61019.4

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #117high of 2201409

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #111high of 2201414

Leader: Gemini 4 · 1553

instruction

IFBench

399 results
  1. #29default of 39975.6%
  2. #191none of 39946.9%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #286default of 52620.7%
  2. #384none of 52615.7%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #239none of 52624.9%
  2. #292default of 52618.5%

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

knowledge

Global-MMLU-Lite

118 results
  1. #29default of 11886.8%
  2. #46none of 11883.8%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #120default of 53985.8%
  2. #148none of 53984.2%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #99default of 26575.0%
  2. #146none of 26570.0%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #126default of 52377.7%
  2. #253none of 52364.0%

Leader: Kimi K3 · 88.7%

other

Arena Vision

116 results
  1. #70high of 1161217

Leader: Fable 5 · 1308

reasoning

CritPt

529 results
  1. #245default of 5290.9%
  2. #270none of 5290.3%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Roboflow Visual Reasoning

102 results
  1. #59high of 10261.6%
  2. #68low of 10258.1%

Leader: GPT-6 Astra · 91.2%

reliability

Tool-call error rate

171 results
  1. #150high of 1715.6%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #141high of 18198.3%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #230none of 3515.6s
  2. #231default of 3515.6s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #203none of 35181.9
  2. #213default of 35176.9

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #127high of 1772.2s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #164high of 17628.0

Leader: Muse Spark 1.1 · 204.3