priorsBuilder

OpenAI · released 2026-09-07

GPT-6 Astra Pro

Measured on 7 benchmarks.

General frontier

70.8

#7 of 136 models · best at xhigh

includes estimates: 15% of the mix is measured for this model

Your mix’s benchmarks

1 of 8 measured

reasoning

SimpleBench

97 results
  1. #3xhigh of 9786.5%

Leader: Opus 5.5 · 88.4%

All 7 benchmarks

show 6 more

coding

WeirdML v2

127 results
  1. #1xhigh of 12793.6%

Leader: this model · 93.6%

creative

MineBench

72 results
  1. #1xhigh of 722281

Leader: this model · 2281

reliability

Tool-call error rate

171 results
  1. #4xhigh of 1710.0%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #91xhigh of 18199.5%

Leader: GPT-5 Pro · 100.0%

speed

Provider latency

177 results
  1. #177xhigh of 17728s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #107xhigh of 17653.0

Leader: Muse Spark 1.1 · 204.3