priorsBuilder

Other · released 2026-04-02

Step 3.5 Flash 2603

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. #181default of 58724.5%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #336default of 526-44.2

Leader: Opus 5.5 · 46.4

All 13 benchmarks

show 11 more

agentic

τ²-Bench Telecom

393 results
  1. #78default of 39387.4%

Leader: GLM 5.2 · 99.1%

coding

Terminal-Bench Hard-AA

387 results
  1. #99default of 38732.6%

Leader: GPT-5.6 Sol · 65.9%

composite

AA Intelligence Index v4.3.2

610 results
  1. #260default of 61017.0

Leader: Opus 5.5 · 57.6

instruction

IFBench

399 results
  1. #94default of 39966.5%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #230default of 52624.6%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #432default of 5268.7%

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

knowledge

GPQA Diamond

539 results
  1. #170default of 53982.6%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #258default of 52363.0%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #193default of 5292.3%

Leader: Muse Wonder Full (Max) · 32.9%

speed

Latency (Time to First Token)

351 results
  1. #213default of 3513.3s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #96default of 351150.2

Leader: Celeris-1 · 1522.5