priorsBuilder

OpenAI · released 2026-04-23

GPT-5.5 Pro

Measured on 14 benchmarks across 2 reasoning efforts.

General frontier

56.5

#24 of 136 models · best at xhigh

includes estimates: 36% of the mix is measured for this model

Reasoning efforts in your mix

xhigh56.5#53 of 313
medium43.9#117 of 313

Your mix’s benchmarks

3 of 8 measured

reasoning

BullshitBench v2

196 results
  1. #107xhigh of 19636.0%
  2. #112medium of 19634.0%

Leader: Opus 4.8 · 95.0%

math

FrontierMath Tier 4 (v2)

70 results
  1. #15xhigh of 7078.0%

Leader: GPT-6.1 Sol · 100.0%

reasoning

SimpleBench

97 results
  1. #11xhigh of 9776.9%

Leader: Opus 5.5 · 88.4%

All 14 benchmarks

show 11 more

creative

MineBench

72 results
  1. #9xhigh of 721959

Leader: GPT-6 Astra Pro · 2281

creative

VoxelBench (text)

55 results
  1. #9xhigh of 551979

Leader: GPT-6 Astra · 2732

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #8xhigh of 11587.7%

Leader: GPT-6.1 Sol · 93.7%

other

T3 Code usage share

85 results
  1. #75xhigh of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #21high of 21596.5%
  2. #34xhigh of 21595.0%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #31high of 21684.6%
  2. #32xhigh of 21684.2%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #14xhigh of 52930.6%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #13xhigh of 1710.1%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #4xhigh of 181100.0%

Leader: GPT-5 Pro · 100.0%

speed

Provider latency

177 results
  1. #148xhigh of 1773.2s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #176xhigh of 17611.0

Leader: Muse Spark 1.1 · 204.3