priorsBuilder

Alibaba · released 2025-04-28

Qwen 3 14B

Measured on 28 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. #481default of 5874.5%
  2. #522none of 5874.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #365default of 526-49.0
  2. #478none of 526-66.7

Leader: Opus 5.5 · 46.4

All 28 benchmarks

show 26 more

agentic

AA-Briefcase v1.1

224 results
  1. #219default of 2240

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #216default of 2190.2%

Leader: Gemini 4 · 77.5%

agentic

τ²-Bench Telecom

393 results
  1. #239default of 39334.5%
  2. #247none of 39332.2%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #179default of 2065.6%

Leader: Qwen 3.8 Max · 51.3%

coding

LiveCodeBench

282 results
  1. #123default of 28252.3%
  2. #194none of 28228.0%

Leader: Gemini 3 Pro · 91.7%

coding

SciCode

226 results
  1. #204default of 22630.7%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench Hard-AA

387 results
  1. #266none of 3875.3%
  2. #288default of 3873.8%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #208default of 2384.9%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #203default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #428default of 6108.2
  2. #489none of 6106.7

Leader: Opus 5.5 · 57.6

economics

GDPval-AA v2.1

288 results
  1. #266default of 288-25

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #252default of 39940.5%
  2. #375none of 39923.9%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #393default of 52615.3%
  2. #430none of 52613.3%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #245default of 52624.2%
  2. #454none of 5267.7%

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

knowledge

GPQA Diamond

539 results
  1. #357default of 53960.4%
  2. #428none of 53947.0%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #126default of 28577.4%
  2. #194none of 28567.5%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #474default of 5230.0%
  2. #484none of 5230.0%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #106none of 22858.0%
  2. #111default of 22855.7%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #29default of 16296.1%
  2. #68none of 16287.1%

Leader: GPT-5 · 99.4%

reasoning

CritPt

529 results
  1. #419default of 5290.0%
  2. #458none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #64none of 1710.9%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #104none of 18199.3%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #71none of 3511.0s
  2. #77default of 3511.0s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #343none of 35126.9
  2. #344default of 35125.3

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #54none of 1770.9s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #121none of 17650.0

Leader: Muse Spark 1.1 · 204.3