priorsBuilder

Alibaba · released 2026-02-13

Qwen 3.5 397B-A17B

Measured on 39 benchmarks.

General frontier

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

Your mix’s benchmarks

3 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #155default of 58729.0%
  2. #208none of 58719.8%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #275default of 526-30.8
  2. #306none of 526-37.9

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #16high of 19678.0%
  2. #30none of 19669.0%

Leader: Opus 4.8 · 95.0%

All 39 benchmarks

show 36 more

agentic

AA-Briefcase v1.1

224 results
  1. #170default of 224562

Leader: Sonnet 5.5 · 1823

agentic

APEX-Agents-AA

33 results
  1. #22default of 3315.3%

Leader: Gemini 3.5 Flash · 47.1%

agentic

AutomationBench-AA

219 results
  1. #151default of 2196.9%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #41default of 5030.9%

Leader: Fable 5 · 51.1%

agentic

ITBench-AA

45 results
  1. #28default of 4534.1%

Leader: GPT-5.6 Sol · 56.2%

agentic

τ²-Bench Telecom

393 results
  1. #22default of 39395.6%
  2. #106none of 39383.9%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #129default of 20613.4%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena WebDev

122 results
  1. #83max of 1221400

Leader: Opus 5.5 · 1813

coding

SciCode

226 results
  1. #144default of 22644.8%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench Hard-AA

387 results
  1. #57default of 38740.9%
  2. #78none of 38735.6%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #119default of 23851.3%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #166default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #209none of 61021.4
  2. #247default of 61018.4

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #77max of 2201442

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #71max of 2201453

Leader: Gemini 4 · 1553

cost

AA Intelligence Index Cost per Task

177 results
  1. #85default of 177$0.47

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #92default of 177$941

Leader: GPT-6 Luna · $10.63

creative

MineBench

72 results
  1. #47max of 721323

Leader: GPT-6 Astra Pro · 2281

economics

GDP.pdf

210 results
  1. #111default of 21012.2%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #184default of 288793

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #13default of 39978.8%
  2. #164none of 39951.6%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #174default of 52630.8%
  2. #231none of 52624.5%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #311none of 52617.3%
  2. #382default of 52611.1%

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

knowledge

Global-MMLU-Lite

118 results
  1. #14default of 11890.0%
  2. #30none of 11886.5%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #79default of 53989.3%
  2. #115none of 53986.1%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #80default of 26577.3%
  2. #221none of 26552.7%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #133default of 52377.3%
  2. #248none of 52364.3%

Leader: Kimi K3 · 88.7%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #70none of 11531.2%
  2. #72max of 11529.5%

Leader: GPT-6.1 Sol · 93.7%

other

Arena Vision

116 results
  1. #56max of 1161246

Leader: Fable 5 · 1308

reasoning

CritPt

529 results
  1. #202default of 5291.7%
  2. #233none of 5290.9%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #155max of 1716.7%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #173max of 18195.3%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #177default of 3512.4s
  2. #179none of 3512.4s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #212default of 35177.1
  2. #225none of 35173.4

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #93max of 1771.3s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #111max of 17653.0

Leader: Muse Spark 1.1 · 204.3