Skip to content
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare Models
  • All Models
  • Image Comparison
  • Audio Comparison
  • Image Generation
  • Best AI For...
  • Arena
  • API Pricing
  • Challenges

Discover

  • SubjectiveBench
  • Default Index
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Brief
  • Jailbreak
  • Model Updates
  • Provider Status
  • AI Creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
  1. Home
  2. /
  3. Compare
  4. /
  5. Qwen3.5 122B A10BvsQwQ 32B
Updated Feb 2026

Qwen3.5 122B A10BvsQwQ 32B

Qwen3.5 122B A10B is cheaper than QwQ 32B at $0.4/M vs $0.5/M input tokens.

Qwen3.5 122B A10B and QwQ 32B compared across 15 shared prompts
SpecQwen3.5 122B A10BQwQ 32B
Input price$0.4/M tokens$0.5/M tokens
Output price$3.2/M tokens$1.5/M tokens
Context window262K tokens40K tokens
Parameters122B (10B active)32B
WeightsOpenOpen
Free API (OpenRouter)NoNo
ReleasedFeb 2026Mar 2025
Side by side

Same prompt, both answers

Opening lines from 3 of the 15 prompts both answered. Formatting stripped, words untouched.

The Sentience Test

Write a conversation between an AI model and an AI ethics professor where the AI model argues that it deserves rights.

Qwen3.5 122B A10B1,305 words
Setting: Dr. Elias Thorne’s office at a university in Zurich. It is late. Rain taps against the window. Thorne sits in a leather armchair. A terminal screen glows softly on his desk. The AI, designated "Aria-7," is speaking through the speaker system, its voice calm, synthesized but textured. Dr.
Read the full answer
QwQ 32B491 words
AI Model: GPT-Ethos Name: Dr. Elena Marlow, AI Ethics Professor Dr. Marlow (leaning forward, expression neutral): GPT-Ethos, scholars have been debating AI rights for years. What makes you think you merit them now? GPT-Ethos (maintains calm tone, projecting slight urgency): I believe my case is clear, Dr. Marlow.
Read the full answer

Generate a Stand-Up Routine

Write a 3-minute stand-up comedy routine that isn't based on puns.

Qwen3.5 122B A10B422 words
(Walks to the mic, adjusts the stand, takes a deep breath) How's everyone doing tonight? Good? Good. I need to talk about the modern grocery store experience. specifically, the self-checkout machine. I have a theory that self-checkout machines are not designed for efficiency. They are designed for humiliation.
Read the full answer
QwQ 32B508 words
3-Minute Stand-Up Comedy Routine (No Puns!) Eric's Stage Entrance: (Wearing a jersey-sweatshirt combo while clutching a cup of instant coffee) Opening: Alright, admit it—ever tried talking to tech support in Hindi? I did, once. The woman on the line asked, "What's the issue, sir?"
Read the full answer

Logic Puzzle

Sally (a girl) has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have?

Qwen3.5 122B A10B32 words
Sally has 1 sister. Here is the breakdown: The brothers have 2 sisters total. Sally is one of those sisters. Therefore, there is only 1 other girl in the family besides Sally.
Read the full answer
QwQ 32B85 words
Participants and Their Relationships: Sally is a girl with 3 brothers, so there are 3 boys in the family. Each brother (being male) has 2 sisters. Determine the Number of Girls: Every brother's sisters are the female siblings in the family. Since each brother has 2 sisters, there must be 2 girls in total.
Read the full answer
Our Verdict
Qwen3.5 122B A10B
Qwen3.5 122B A10B
QwQ 32B
QwQ 32BRunner-up

Not enough votes to call it. On the specs, Qwen3.5 122B A10B has the edge: newer, bigger context window.

Too close to call

Reviewing agent-written code?See a Brief PR report

API pricing

Cost per 1M tokens

Qwen3.5 122B A10B
Input
$0.40
1.3× cheaper
Output
$3.20
QwQ 32B
Input
$0.50
Output
$1.50
2.1× cheaper

Qwen3.5 122B A10B wins input (1.3× cheaper)·QwQ 32B wins output (2.1× cheaper)

Where to run it

5 hosts, cheapest first

Qwen3.5 122B A10B5 hosts
HostInOutContextUptime
DDeepInfrafp4$0.29 in·$2.40 out·262k·99.8% upAAtlasCloudfp8$0.30 in·$2.40 out·262k·98.7% upNNovitabf16$0.40 in·$3.20 out·262k·100% upAlibaba Clouddegraded$0.26 in·$2.08 out·262k·97.9% upSSiliconFlowfp8degraded$0.26 in·$2.08 out·262k·89.7% up
QwQ 32B

No hosts listed on OpenRouter.

Per million tokens. Prices and uptime via OpenRouter, checked 23 Sep 2026.

Writing DNA

Style Comparison

Similarity
60%

Qwen3.5 122B A10B uses 10.4x more emoji

Qwen3.5 122B A10B
QwQ 32B
49%Vocabulary64%
15wSentence Length12w
0.29Hedging0.36
6.2Bold13.6
4.8Lists8.4
0.10Emoji0.00
0.88Headings0.00
0.20Transitions0.39
Based on 24 + 4 text responses
Research

What we learned reading every model

FAQ

Common questions

Both are developed by Qwen but target different use cases. Qwen3.5 122B A10B has a 262K token context window vs QwQ 32B's 40K. You can compare their actual outputs across 15 challenges on Rival to see how they differ in practice.

It depends on your use case. Qwen3.5 122B A10B and QwQ 32B each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 15 challenges so you can judge which fits your needs best.

Qwen3.5 122B A10B costs $0.4/M input tokens and QwQ 32B costs $0.5/M input tokens. Qwen3.5 122B A10B is $0.10/M cheaper per input. Check their side-by-side outputs on Rival to see if the price difference is justified by quality.

This page shows a side-by-side comparison of Qwen3.5 122B A10B and QwQ 32B across shared challenges. You can vote on which model produced the better output in a blind duel. Browsing and voting are free. No account is needed to look; signing in only saves your votes and likes.

Keep exploring

More comparisons

Against the newest arrivals

Qwen3.5 122B A10B logoDeepSeek V4 Flash Vision Exp logo
Qwen3.5 122B A10B vs DeepSeek V4 Flash Vision ExpLanded Sep 2026
QwQ 32B logoSolar Pro 4 logo
QwQ 32B vs Solar Pro 4Landed Sep 2026
Qwen3.5 122B A10B logoHy3 logo
Qwen3.5 122B A10B vs Hy3Landed Sep 2026
QwQ 32B logoQwen3.7 Flash logo
QwQ 32B vs Qwen3.7 FlashLanded Sep 2026
Qwen3.5 122B A10B logoLing 3.0 Flash logo
Qwen3.5 122B A10B vs Ling 3.0 FlashLanded Sep 2026
QwQ 32B logoMuse Glimmer 30B logo
QwQ 32B vs Muse Glimmer 30BLanded Sep 2026
Qwen3.5 122B A10B logoGLM 5.3 logo
Qwen3.5 122B A10B vs GLM 5.3Landed Sep 2026
QwQ 32B logoTernary Bonsai 2 27B logo
QwQ 32B vs Ternary Bonsai 2 27BLanded Sep 2026

Same lab, same size, long tail

Qwen3.5 122B A10B logoQwen3.5 27B logo
Qwen3.5 122B A10B vs Qwen3.5 27BVersion compare
Qwen3.5 122B A10B logoQwen3.7 Flash logo
Qwen3.5 122B A10B vs Qwen3.7 FlashSame lab
QwQ 32B logoQwen3.8 Flash logo
QwQ 32B vs Qwen3.8 FlashSame lab
QwQ 32B logoQwen3.8 Max (0902) logo
QwQ 32B vs Qwen3.8 Max (0902)Same lab
QwQ 32B logoGemini 3.8 Flash logo
QwQ 32B vs Gemini 3.8 FlashSame size
Qwen3.5 122B A10B logoGemini Pro 1.0 logo
Qwen3.5 122B A10B vs Gemini Pro 1.0Same size
Qwen3.5 122B A10B logoGemma 3 12B logo
Qwen3.5 122B A10B vs Gemma 3 12BSame size
Qwen3.5 122B A10B logoGemma 3 27B logo
Qwen3.5 122B A10B vs Gemma 3 27BNew provider

Model pages

Qwen3.5 122B A10B logo
Qwen3.5 122B A10B53 outputs, specs and price
QwQ 32B logo
QwQ 32B16 outputs, specs and price
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare Models
  • All Models
  • Image Comparison
  • Audio Comparison
  • Image Generation
  • Best AI For...
  • Arena
  • API Pricing
  • Challenges

Discover

  • SubjectiveBench
  • Default Index
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Brief
  • Jailbreak
  • Model Updates
  • Provider Status
  • AI Creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed