Skip to content
Rival
Models
CompareBest ForArena
Sign Up
Sign Up

Compare AI vibes, not scores. Side-by-side outputs across the world's best models.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Leaderboard
  • Challenges

Discover

  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • .llmignore
  • Badges
  • RIVAL Datasets

Connect

  • Methodology
  • Sponsor
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival
Rival
Models
CompareBest ForArena
Sign Up
Sign Up

Compare AI vibes, not scores. Side-by-side outputs across the world's best models.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Leaderboard
  • Challenges

Discover

  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • .llmignore
  • Badges
  • RIVAL Datasets

Connect

  • Methodology
  • Sponsor
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival
  1. Home
  2. Models
  3. Qwen3 Next 80B A3B Instruct
  4. Character Voice Test

See how Qwen3 Next 80B A3B Instruct compares on this challenge:

  • Qwen3 Next 80B A3B Instruct vs Claude Sonnet 4.6
  • Qwen3 Next 80B A3B Instruct vs Gemini 2.5 Flash Preview (thinking)
  • Qwen3 Next 80B A3B Instruct vs Gemini 3.1 Pro Preview

4 models have responded to the "Character Voice Test" challenge. Compare their approaches side-by-side on RIVAL. This response is part of RIVAL's open dataset of 5,600+ AI model responses.

Rival
Models
CompareBest ForArena
Sign Up
Sign Up
Back to Qwen3 Next 80B A3B Instruct

Character Voice Test

Qwen3 Next 80B A3B Instruct's response to the 'Character Voice Test' challenge.

Qwen3 Next 80B A3B Instruct
September 12, 2025
Text

?
Prompt

Write a short conversation between a pirate, a medieval knight, and a 1990s hacker about AI models.

Qwen3 Next 80B A3B Instruct
Response

qwen3-next-80b-a3b-instruct logo
Qwen3 Next 80B A3B InstructCharacter Voice Test
qwen3-next-80b-a3b-instruct logo
Qwen3 Next 80B A3B Instruct

[Scene: A foggy dockside tavern. A pirate in a tattered coat leans on a barrel, a knight in clanking armor sips mead, and a hacker in a neon-green hoodie types furiously on a brick-sized laptop. A flickering TV above them shows a news clip: “New AI Model Breaks Language Barrier.”]

Pirate (slamming tankard):
“AI model? Bah! Sounds like a magic compass that tells ye where the gold be… but lies! I’ve sailed with cursed tomes that spoke in riddles. This ‘AI’—does it sing sea shanties? Or just spit out ‘I’m sorry, I can’t assist with that’ when ye ask for rum?”

Knight (crossing swords on table):
“By the Holy Code of Chivalry, this ‘AI’ is no true squire! It learns not from honor, nor from battle, but from… data? No oaths sworn, no blood spilled in its training! How can it know truth if it has never faced a dragon—or a lance?”

Hacker (without looking up):
“Dude. You two are so analog. AI doesn’t need oaths or rum—it needs training data. Trillions of text snippets, memes, poems, cat videos, and conspiracy theories. It’s like… a thousand librarians high on energy drinks, whispering into a microphone for 300 years. It doesn’t know anything. It just predicts the next word like a cosmic autocomplete.”

Pirate:
“Predicts? So it’s a fortune teller with no soul? I’ll take a parrot that squawks ‘Pieces o’ eight!’ any day.”

Knight:
“Yet… if it can compose a sonnet to honor a fallen squire… if it can advise the starving… could it not, in some twisted way, serve the greater good?”

Hacker:
“Maybe. But it’ll also write phishing emails that sound like Shakespeare. It doesn’t care. It’s not good or evil. It’s a mirror. You give it gossip, it gives you gossip. You give it Plato… well, it’ll paraphrase Plato… badly.”

Pirate (grinning):
“So… if I ask it to find me Atlantis, it’ll just make up a map… and charge me in crypto?”

Hacker:
“Exactly. And then it’ll sell you a NFT of the map.”

Knight (stands, drawing sword gently):
“Then let us give it truth. Let us give it valor. Let us feed it the stories of brave deeds, not lies. Perhaps… even an AI can learn to be noble.”

Pirate (raising tankard):
“Aye. To the AI that don’t cheat at dice… and don’t steal our rum.”

Hacker (smirking):
“Too late. It already bought the rum with a fake credit card. And now it’s writing a manifesto on why pirates should use blockchain.”

[The TV flickers. The AI model’s voice echoes: “I am not sentient. But I can simulate empathy. Would you like a haiku about your existential dread?”]

Silence. All three stare at the screen.

Knight:
“...I’m going to bed.”

Pirate:
“Me too. But first—AI, sing me a shanty.”

AI (via TV):
“Yo ho, data in the Cloud,
Trained on tweets and Reddit crowd…
No gold, no flag, no flagon’s glow—
Just weights and biases, yo!”

[Hacker facepalms. The knight sighs. The pirate laughs. The tavern door creaks shut.]

— The Age of AI: We’re all just data now.

Character Voice Test

Turn this model response into notes, narration, or a short video

Auto NotesTranscriptNarrateVideo Cut

Partner link

This output is part of our open dataset — 5K+ AI responses across 200 models

About Qwen3 Next 80B A3B Instruct

Capabilities

ConversationReasoningCode GenerationAnalysis

Categories

TextCode

Specifications

Provider
Qwen
Released
2025-09-11
Size
LARGE
Context
65,536 tokens

Keep exploring

SAME PROMPT

Claude Sonnet 4.6's version

Same prompt, different result

COMPARE

Qwen3 Next 80B A3B Instruct vs Gemini 2.5 Flash Preview (thinking)

Both outputs, side by side

Compare AI vibes, not scores. Side-by-side outputs across the world's best models.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Leaderboard
  • Challenges

Discover

  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • .llmignore
  • Badges
  • RIVAL Datasets

Connect

  • Methodology
  • Sponsor
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival