priorsBuilder

Ant Group · released 2026-04-21

Ling 2.6 Flash

Measured on 14 benchmarks.

General frontier

10.2

#130 of 136 models · best at none

includes estimates: 24% of the mix is measured for this model

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #383none of 5876.3%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #476none of 526-66.1

Leader: Opus 5.5 · 46.4

All 14 benchmarks

show 12 more

agentic

τ²-Bench Telecom

393 results
  1. #93none of 39386.0%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #201none of 2062.9%

Leader: Qwen 3.8 Max · 51.3%

coding

Terminal-Bench Hard-AA

387 results
  1. #163none of 38721.2%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #170none of 23824.3%

Leader: Fable 5.1 · 91.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #381none of 6109.7

Leader: Opus 5.5 · 57.6

economics

GDPval-AA v2.1

288 results
  1. #237none of 288318

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #136none of 39957.4%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #388none of 52615.6%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #518none of 5263.3%

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

knowledge

GPQA Diamond

539 results
  1. #364none of 53959.3%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #373none of 52331.3%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #389none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%