priorsBuilder

Other · released 2026-02-02

Step 3.5 Flash

Measured on 13 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. #202default of 58721.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #319default of 526-41.8

Leader: Opus 5.5 · 46.4

All 13 benchmarks

show 11 more

agentic

τ²-Bench Telecom

393 results
  1. #32default of 39394.4%

Leader: GLM 5.2 · 99.1%

coding

Terminal-Bench Hard-AA

387 results
  1. #127default of 38727.3%

Leader: GPT-5.6 Sol · 65.9%

composite

AA Intelligence Index v4.3.2

610 results
  1. #267default of 61016.6

Leader: Opus 5.5 · 57.6

instruction

IFBench

399 results
  1. #106default of 39964.6%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #246default of 52623.6%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #341default of 52614.3%

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

knowledge

GPQA Diamond

539 results
  1. #160default of 53983.1%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #305default of 52350.0%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #190default of 5292.5%

Leader: Muse Wonder Full (Max) · 32.9%

speed

Latency (Time to First Token)

351 results
  1. #214default of 3513.3s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #91default of 351154.5

Leader: Celeris-1 · 1522.5