priorsBuilder

OpenAI · released 2026-05-05

GPT-5.5 Instant

Measured on 29 benchmarks across 3 reasoning efforts.

General frontier

30.2

#81 of 136 models

includes estimates: 16% of the mix is measured for this model

Reasoning efforts in your mix

default30.2#220 of 313
default27.6#234 of 313
default26.0#241 of 313

Your mix’s benchmarks

3 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #198default of 58721.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #89default of 52611.2

Leader: Opus 5.5 · 46.4

math

FrontierMath Tier 4 (v2)

70 results
  1. #63default of 702.4%

Leader: GPT-6.1 Sol · 100.0%

All 29 benchmarks

show 26 more

agentic

AA-Briefcase v1.1

224 results
  1. #106default of 2241086

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #100default of 21936.4%

Leader: Gemini 4 · 77.5%

agentic

τ²-Bench Telecom

393 results
  1. #201default of 39349.4%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #138default of 20611.8%

Leader: Qwen 3.8 Max · 51.3%

coding

SciCode

226 results
  1. #81default of 22652.5%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench Hard-AA

387 results
  1. #48default of 38742.4%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #150default of 23834.8%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #80default of 21612.6%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #151default of 61026.0

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #41default of 2201473

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #34default of 2201482

Leader: Gemini 4 · 1553

cost

AA Intelligence Index Cost per Task

177 results
  1. #100default of 177$0.69

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #105default of 177$1,184

Leader: GPT-6 Luna · $10.63

economics

GDP.pdf

210 results
  1. #62default of 21020.2%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #214default of 288509

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #53default of 39971.5%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #81default of 52646.3%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #184default of 52634.7%

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

knowledge

GPQA Diamond

539 results
  1. #137default of 53984.6%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #210default of 52370.0%

Leader: Kimi K3 · 88.7%

long-context

Arena Document

43 results
  1. #42default of 431403

Leader: Opus 5 · 1516

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #75default of 11526.3%

Leader: GPT-6.1 Sol · 93.7%

other

Arena Vision

116 results
  1. #32default of 1161276

Leader: Fable 5 · 1308

reasoning

CritPt

529 results
  1. #182default of 5292.6%

Leader: Muse Wonder Full (Max) · 32.9%

speed

Latency (Time to First Token)

351 results
  1. #57default of 3510.9s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #88default of 351156.3

Leader: Celeris-1 · 1522.5