priorsBuilder

Alibaba · released 2026-02-24

Qwen 3.5 122B-A10B

Measured on 33 benchmarks.

General frontier

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

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #179default of 58725.2%
  2. #239none of 58715.9%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #316default of 526-41.5
  2. #413none of 526-55.0

Leader: Opus 5.5 · 46.4

All 33 benchmarks

show 31 more

agentic

AA-Briefcase v1.1

224 results
  1. #174default of 224497

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #157default of 2195.5%

Leader: Gemini 4 · 77.5%

agentic

τ²-Bench Telecom

393 results
  1. #42default of 39393.6%
  2. #103none of 39384.5%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #119default of 20615.3%
  2. #143none of 20610.3%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena WebDev

122 results
  1. #95none of 1221360

Leader: Opus 5.5 · 1813

coding

SciCode

226 results
  1. #173default of 22639.7%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench Hard-AA

387 results
  1. #112default of 38731.1%
  2. #118none of 38729.5%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #124default of 23847.6%
  2. #125none of 23847.2%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #172default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #253none of 61017.7
  2. #275default of 61015.6

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #107none of 2201416

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #108none of 2201419

Leader: Gemini 4 · 1553

cost

AA Intelligence Index Cost per Task

177 results
  1. #72default of 177$0.32

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #82default of 177$661

Leader: GPT-6 Luna · $10.63

economics

GDP.pdf

210 results
  1. #173default of 2103.4%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #183default of 288814
  2. #195none of 288709

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #28default of 39975.7%
  2. #168none of 39950.8%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #234default of 52624.4%
  2. #305none of 52619.1%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #357default of 52612.9%
  2. #440none of 5268.4%

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

knowledge

Global-MMLU-Lite

118 results
  1. #22default of 11889.1%
  2. #34none of 11885.9%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #124default of 53985.7%
  2. #168none of 53982.7%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #101default of 26575.0%
  2. #142none of 26570.3%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #143default of 52376.3%
  2. #264none of 52361.3%

Leader: Kimi K3 · 88.7%

other

Arena Vision

116 results
  1. #67none of 1161226

Leader: Fable 5 · 1308

reasoning

CritPt

529 results
  1. #239none of 5290.9%
  2. #254default of 5290.6%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #122none of 1712.9%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #167none of 18196.6%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #172none of 3512.3s
  2. #173default of 3512.3s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #98none of 351142.7
  2. #110default of 351128.1

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #82none of 1771.2s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #78none of 17671.0

Leader: Muse Spark 1.1 · 204.3