priorsBuilder

Alibaba · released 2025-09-23

Qwen 3

Measured on 33 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. #269default of 58712.6%
  2. #347none of 5877.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #348default of 526-46.5
  2. #388none of 526-51.9

Leader: Opus 5.5 · 46.4

All 33 benchmarks

show 31 more

agentic

OSWorld-Verified

13 results
  1. #10high of 1341.6%

Leader: Fable 5 · 86.0%

agentic

τ²-Bench Telecom

393 results
  1. #192default of 39354.1%
  2. #237none of 39335.1%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #170default of 2066.2%

Leader: Qwen 3.8 Max · 51.3%

coding

LiveCodeBench

282 results
  1. #32default of 28278.4%
  2. #74none of 28268.4%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #211default of 38711.4%
  2. #232none of 3878.3%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #201default of 2386.7%

Leader: Fable 5.1 · 91.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #303default of 61013.4
  2. #374none of 6109.9

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #112high of 2201413

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #101high of 2201425

Leader: Gemini 4 · 1553

economics

GDPval-AA v2.1

288 results
  1. #256default of 288128

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #124default of 39960.7%
  2. #234none of 39942.7%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #281default of 52620.8%
  2. #288none of 52620.5%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #319default of 52616.3%
  2. #423none of 5269.0%

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

knowledge

Global-MMLU-Lite

118 results
  1. #56default of 11881.9%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #220default of 53977.2%
  2. #258none of 53973.8%

Leader: GPT-6 Astra · 96.3%

knowledge

MedCode

94 results
  1. #84high of 9431.7%

Leader: Opus 5 · 63.6%

knowledge

MedScribe

96 results
  1. #62high of 9677.1%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU-Pro

285 results
  1. #46default of 28583.6%
  2. #59none of 28582.3%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU-Pro

265 results
  1. #158default of 26568.7%
  2. #161none of 26567.6%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #257default of 52363.7%
  2. #301none of 52352.7%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #34default of 22888.3%
  2. #81none of 22872.3%

Leader: GPT-5.2 · 99.0%

other

Arena Vision

116 results
  1. #73high of 1161215

Leader: Fable 5 · 1308

reasoning

CritPt

529 results
  1. #281default of 5290.3%
  2. #385none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Roboflow Visual Reasoning

102 results
  1. #97high of 10233.8%
  2. #101low of 10229.8%

Leader: GPT-6 Astra · 91.2%

reasoning

SAGE

80 results
  1. #53high of 8042.1%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

171 results
  1. #93high of 1711.5%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #118high of 18198.9%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #150default of 3511.9s
  2. #209none of 3513.2s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #75none of 351164.2
  2. #85default of 351156.5

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #71high of 1771.1s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #156high of 17632.0

Leader: Muse Spark 1.1 · 204.3