priorsBuilder

Alibaba · released 2026-03-02

Qwen 3.5 2B

Measured on 15 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. #448none of 5875.0%
  2. #584default of 5872.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #442default of 526-60.2
  2. #521none of 526-83.1

Leader: Opus 5.5 · 46.4

All 15 benchmarks

show 13 more

agentic

τ²-Bench Telecom

393 results
  1. #117none of 39381.6%
  2. #162default of 39369.0%

Leader: GLM 5.2 · 99.1%

coding

Terminal-Bench Hard-AA

387 results
  1. #291default of 3873.8%
  2. #292none of 3873.8%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #220default of 2383.0%
  2. #234none of 2380.0%

Leader: Fable 5.1 · 91.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #481default of 6106.9
  2. #512none of 6106.2

Leader: Opus 5.5 · 57.6

economics

GDPval-AA v2.1

288 results
  1. #268default of 288-46
  2. #279none of 288-367

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #333default of 39931.5%
  2. #346none of 39929.1%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #492default of 5268.1%
  2. #497none of 5267.4%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #232default of 52625.8%
  2. #522none of 5262.3%

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

knowledge

GPQA Diamond

539 results
  1. #433default of 53945.6%
  2. #439none of 53943.8%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #243default of 26543.0%
  2. #245none of 26542.7%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #411default of 52321.0%
  2. #436none of 52314.0%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #452default of 5290.0%
  2. #469none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Roboflow Visual Reasoning

102 results
  1. #102low of 10227.1%

Leader: GPT-6 Astra · 91.2%