priorsBuilder

Alibaba · released 2026-08-26

Qwen 3.8 Flash

Measured on 29 benchmarks.

General frontier

39.2

#63 of 136 models

includes estimates: 24% of the mix is measured for this model

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #98default of 58738.0%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #183default of 526-9.7

Leader: Opus 5.5 · 46.4

All 29 benchmarks

show 27 more

agentic

AA-Briefcase v1.1

224 results
  1. #18default of 2241581

Leader: Sonnet 5.5 · 1823

agentic

Agent Arena

50 results
  1. #33max of 50-0.7%

Leader: Opus 5.5 · 15.5%

agentic

AutomationBench-AA

219 results
  1. #53default of 21955.9%

Leader: Gemini 4 · 77.5%

agentic

τ³-Banking

206 results
  1. #14default of 20645.4%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena WebDev

122 results
  1. #16max of 1221633

Leader: Opus 5.5 · 1813

coding

SciCode

226 results
  1. #99default of 22650.6%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #22default of 23886.1%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #52default of 21625.3%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #61default of 61039.8

Leader: Opus 5.5 · 57.6

cost

AA Intelligence Index Cost per Task

177 results
  1. #79default of 177$0.37

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #58default of 177$363

Leader: GPT-6 Luna · $10.63

economics

GDP.pdf

210 results
  1. #90default of 21015.6%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #21default of 2881629

Leader: Opus 5.5 · 1866

knowledge

AA-Omniscience Accuracy

526 results
  1. #232default of 52624.5%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #97default of 52654.7%

Leader: MiniCPM5-1B (Non-reasoning) · 99.1%

knowledge

GPQA Diamond

539 results
  1. #36default of 53992.3%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #54default of 26579.8%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #90default of 52379.7%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #108default of 52911.1%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Humanity's Sixth Sense

25 results
  1. #13max of 2530.9%

Leader: GPT-6 Astra · 53.6%

reasoning

Roboflow Visual Reasoning

102 results
  1. #40high of 10269.5%
  2. #94low of 10235.1%

Leader: GPT-6 Astra · 91.2%

reliability

Tool-call error rate

171 results
  1. #127high of 1713.5%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #95high of 18199.4%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #152default of 3512.0s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #295default of 35151.6

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #100high of 1771.4s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #106high of 17653.0

Leader: Muse Spark 1.1 · 204.3