priorsBuilder

Alibaba · released 2026-04-27

Qwen 3.6 Flash

Measured on 6 benchmarks.

General frontier

25.8

#90 of 136 models · best at max

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

Your mix’s benchmarks

1 of 8 measured

reasoning

SimpleBench

97 results
  1. #72max of 9735.2%

Leader: Opus 5.5 · 88.4%

All 6 benchmarks

show 5 more

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #82none of 11522.5%
  2. #96max of 11517.2%

Leader: GPT-6.1 Sol · 93.7%

reliability

Tool-call error rate

171 results
  1. #165max of 1719.9%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #33max of 181100.0%

Leader: GPT-5 Pro · 100.0%

speed

Provider latency

177 results
  1. #7max of 1770.4s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #27max of 176105.5

Leader: Muse Spark 1.1 · 204.3