priorsBuilder

Alibaba · released 2025-04-28

Qwen 3 1.7B

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. #421none of 5875.3%
  2. #472default of 5874.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #508default of 526-77.5
  2. #522none of 526-84.1

Leader: Opus 5.5 · 46.4

All 16 benchmarks

show 14 more

agentic

τ²-Bench Telecom

393 results
  1. #283default of 39326.0%
  2. #311none of 39321.6%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #178default of 28230.8%
  2. #246none of 28212.6%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #368default of 3870.0%
  2. #375none of 3870.0%

Leader: GPT-5.6 Sol · 65.9%

composite

AA Intelligence Index v4.3.2

610 results
  1. #577default of 6105.2
  2. #591none of 6104.9

Leader: Opus 5.5 · 57.6

instruction

IFBench

399 results
  1. #358default of 39926.9%
  2. #390none of 39921.1%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #483default of 5268.9%
  2. #501none of 5266.9%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #495default of 5265.2%
  2. #523none of 5262.2%

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

knowledge

Global-MMLU-Lite

118 results
  1. #115none of 11848.8%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #472default of 53935.6%
  2. #514none of 53928.3%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #227default of 28557.0%
  2. #259none of 28541.1%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #506default of 5230.0%
  2. #511none of 5230.0%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #137default of 22838.7%
  2. #201none of 2287.3%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #59default of 16289.4%
  2. #110none of 16271.7%

Leader: GPT-5 · 99.4%

reasoning

CritPt

529 results
  1. #499default of 5290.0%
  2. #508none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%