priorsBuilder

OpenAI · released 2025-12-11

GPT-5.2 Pro

Measured on 11 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

2 of 8 measured

math

FrontierMath Tier 4 (v2)

70 results
  1. #26xhigh of 7046.0%

Leader: GPT-6.1 Sol · 100.0%

reasoning

SimpleBench

97 results
  1. #43xhigh of 9757.4%

Leader: Opus 5.5 · 88.4%

All 11 benchmarks

show 9 more

creative

MineBench

72 results
  1. #33xhigh of 721588

Leader: GPT-6 Astra Pro · 2281

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #21xhigh of 11574.0%

Leader: GPT-6.1 Sol · 93.7%

other

T3 Code usage share

85 results
  1. #81xhigh of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #65xhigh of 21590.5%
  2. #96high of 21585.7%
  3. #104medium of 21581.2%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #91high of 21654.2%
  2. #105medium of 21638.5%

Leader: GPT-6 Astra · 95.0%

reliability

Tool-call error rate

172 results
  1. #51xhigh of 1720.6%

Leader: Gemini 4 · 0.0%

reliability

Uptime (7d)

182 results
  1. #16xhigh of 182100.0%

Leader: GPT-5 Pro · 100.0%

speed

Provider latency

178 results
  1. #175xhigh of 1789.8s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #174xhigh of 17614.0

Leader: Muse Spark 1.1 · 204.5