priorsBuilder

Alibaba · released 2025-08-06

Qwen 3 4B

Measured on 16 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. #390default of 5876.2%
  2. #484none of 5874.5%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #444default of 526-60.3
  2. #452none of 526-61.9

Leader: Opus 5.5 · 46.4

All 16 benchmarks

show 14 more

agentic

τ²-Bench Telecom

393 results
  1. #279none of 39326.6%
  2. #286default of 39325.4%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #90default of 28264.1%
  2. #161none of 28237.7%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #278none of 3874.5%
  2. #319default of 3871.5%

Leader: GPT-5.6 Sol · 65.9%

composite

AA Intelligence Index v4.3.2

610 results
  1. #410default of 6108.8
  2. #487none of 6106.7

Leader: Opus 5.5 · 57.6

instruction

IFBench

399 results
  1. #172default of 39949.8%
  2. #312none of 39933.5%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #443default of 52612.5%
  2. #459none of 52610.9%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #296none of 52618.3%
  2. #315default of 52616.8%

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

knowledge

Global-MMLU-Lite

118 results
  1. #107none of 11867.7%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #318default of 53966.7%
  2. #405none of 53951.7%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #155default of 28574.3%
  2. #195none of 28567.2%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #354default of 52337.3%
  2. #443none of 52311.3%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #52default of 22882.7%
  2. #114none of 22852.3%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #45default of 16293.3%
  2. #79none of 16284.3%

Leader: GPT-5 · 99.4%

reasoning

CritPt

529 results
  1. #405default of 5290.0%
  2. #457none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%