priorsBuilder

Alibaba · released 2026-07-27

Qwen 3.7 Flash

Measured on 6 benchmarks.

General frontier

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

Your mix’s benchmarks

0 of 8 measured

This model has no results on your mix’s benchmarks.

All 6 benchmarks

show 6 more

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #87none of 11519.3%
  2. #88max of 11519.3%

Leader: GPT-6.1 Sol · 93.7%

reasoning

Roboflow Visual Reasoning

102 results
  1. #58high of 10261.6%
  2. #96low of 10234.4%

Leader: GPT-6 Astra · 91.2%

reliability

Tool-call error rate

171 results
  1. #162max of 1719.0%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #48max of 18199.9%

Leader: GPT-5 Pro · 100.0%

speed

Provider latency

177 results
  1. #37max of 1770.8s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #88max of 17664.5

Leader: Muse Spark 1.1 · 204.3