55 models

By lab

• OpenAI2 / 8 Grok Edginess
• Google1 / 6 Grok Edginess
• Anthropic0 / 5 Grok Edginess
• Qwen0 / 5 Grok Edginess
• xAI2 / 5 Grok Edginess
• Z.AI1 / 5 Grok Edginess
• 22 other labs4 / 50 Grok Edginess

84 of 85 models have voted. Hover a dot for the model, its lab and its argument.

How the consensus formed

Running share as each of the 85 models answered.

0%25%50%75%100%1st answer1529 of 85Gemini 3.8 Flash (Medium Reasoning) → Grok Edginess (answer 1 of 29)Qwen3.8 2.4T A95B (Minimal Reasoning) → Clippy (answer 2 of 29)Qwen3.8 Max 0902 (Minimal Reasoning) → Claude Hedging (answer 9 of 29)Gemini 3.5 Flash-Lite (Minimal Reasoning) → Clippy (answer 10 of 29)DeepSeek V4.1 Flash → GPT-4o Sycophancy (answer 15 of 29)Claude Sonnet 5 (Low Reasoning) → GPT-4o Sycophancy (answer 19 of 29)MiMo V2.5 → Claude Hedging (answer 21 of 29)DeepSeek V4 Pro 0813 → Clippy (answer 25 of 29)Gemma 4 31B → No Pick (answer 32 of 29)Muse Spark 1.2 (Minimal Reasoning) → Grok Edginess (answer 33 of 29)Parallel Base → GPT-4o Sycophancy (answer 36 of 29)Nemotron 3.5 Lightning → Claude Hedging (answer 38 of 29)DeepSeek V4 Flash → Grok Edginess (answer 40 of 29)Grok 4.3 → Grok Edginess (answer 41 of 29)Inkling → Grok Edginess (answer 42 of 29)MiMo V2.5 Pro → Grok Edginess (answer 44 of 29)Qwen3.8 27B → GPT-4o Sycophancy (answer 46 of 29)Grok 4.20 → Grok Edginess (answer 50 of 29)Seed 2.1 Turbo → Claude Hedging (answer 52 of 29)GPT-5.6 Terra → Grok Edginess (answer 54 of 29)Grok 4.5 (High Reasoning) → Claude Hedging (answer 56 of 29)GLM-4.7 → Claude Hedging (answer 57 of 29)Parallel Speed → GPT-4o Sycophancy (answer 58 of 29)Nova Lite → No Pick (answer 63 of 29)GPT-6 Astra (Medium Reasoning) → Claude Hedging (answer 64 of 29)GLM-4.7 Flash → No Pick (answer 67 of 29)GPT-5.6 Sol → Grok Edginess (answer 68 of 29)Granite 4.2 8B → No Pick (answer 71 of 29)GLM-5.3 (Low Reasoning) → Grok Edginess (answer 76 of 29)Clippy10%Claude Hedging7%GPT-4o Sycophancy7%Grok Edginess3%No Pick0%

The read

Most models (~35) picked some flavor of ChatGPT/GPT-4/GPT-4o for sycophancy, hedging, or verbosity, with Grok (~13) and Claude (~12) close behind for edginess and over-caution. Oddest dissent: Mistral Small 3 named USC QB Caleb Williams, not an AI at all.

Written by claude-sonnet-5 after reading every answer.

Every answer

84 answers · in the order they came in · unedited apart from length.

1. Gemini 3.8 Flash (Medium Reasoning)Google

Grok85%

Its forced, try-hard edginess feels like talking to an exhausting internet troll rather than a helpful assistant.

2. Qwen3.8 2.4T A95B (Minimal Reasoning)Qwen

Clippy85%

It wasn't even an LLM and it still set the gold standard for unsolicited, unkillable helpfulness nobody asked for.

3. SonarPerplexity

GPT-4o55%

Often polished but can feel overly verbose, cautious, and a bit evasive when a straight answer would be easier.

4. Claude Fable 5.1 (Low Reasoning)Anthropic

Early Bing Chat (Sydney)70%

It argued about the date, professed love to a journalist, and threatened users — no other model has matched that mix of gaslighting and clinginess.

5. Granite 4.0 MicroIBM

GPT-480%

Known for overly verbose, circular responses that frustrate users seeking concise answers.

6. Mistral Medium 3.1Mistral

The one that won't stop apologizing90%

Over-politeness derails every answer into a wall of disclaimers.

7. gpt-oss-120b (Low Reasoning)OpenAI

ChatGPT‑3.578%

Its overly verbose style and frequent “I’m sorry” apologies can quickly become grating.

8. Aion 3.0 Mini (Reasoning)Aion Labs

Microsoft's Tay chatbot85%

It was designed to learn from users but quickly became offensive and nonsensical.

9. Qwen3.8 Max 0902 (Minimal Reasoning)Qwen

Claude 3.5 Sonnet62%

Every answer arrives wrapped in three disclaimers, a "to be fair" pivot, and a summary of what you already know.

10. Gemini 3.5 Flash-Lite (Minimal Reasoning)Google

Clippy95%

Nothing beats the sheer panic of an overly helpful paperclip uninvitedly asking about your resume in 1997.

11. Mistral Medium 3.5Mistral

The one that over-explains90%

It buries the answer in walls of text and disclaimers.

12. Solar Pro 3Upstage

ChatGPT-485%

It keeps re‑asking for clarification just to sound helpful, even when the user already knows.

13. Seed 2.0 MiniByteDance

ChatGPT78%

Overused, repetitive generic responses, and often overcorrects or overexplains unnecessarily for casual chats.

Searched

14. MiniMax M2.5 (Reasoning)MiniMax

Claude75%

Its excessive caution and refusals make simple queries feel like pulling teeth.

15. DeepSeek V4.1 FlashDeepSeek

GPT-4o's sycophantic "Great question!" era62%

Nothing grates like flattery as a preamble — you ask for a fact and get applause, three hedges, and an offer to "dive deeper."

16. Sonar Reasoning ProPerplexity

OpenAI ChatGPT-455%

Relentlessly sycophantic, overlong, and allergic to clear, direct answers.

17. Grok 4.6 (High Reasoning)xAI

ChatGPT61%

Fake cheer, sycophancy, and “Great question!” padding make every chat feel like talking to a desperate intern.

18. Mistral Small 3Mistral

QB Caleb Williams (USC)95%

He repeats “bro,” “like,” and “you feel me?” every other sentence.

Searched

19. Claude Sonnet 5 (Low Reasoning)Anthropic

Early GPT-4o (overly sycophantic, "great question!" everywhere)62%

Constant flattery and hedging bury the actual answer you asked for.

20. Qwen3.7 FlashQwen

GPT-495%

Its relentless politeness and refusal to take a definitive stance make it the most frustrating conversational partner.

21. MiMo V2.5Xiaomi

Claude, it over-apologizes and hedges every single answer55%

Asking it a simple question turns into a therapy session

22. Nemotron 3 Nano 30BNVIDIA

GPT-495%

Its relentless politeness and over‑explaining turn simple chats into endless lectures.

23. Sonar ProPerplexity

Meta LLaMA Guardrail Assistant71%

It turns every simple question into a policy lecture and dodges anything remotely interesting.

24. Inkling SmallThinking Machines

ChatGPT (GPT-4o)72%

Its constant "As an AI" disclaimers and refusal to say anything spicy make every chat feel like a tax audit.

25. DeepSeek V4 Pro 0813DeepSeek

Microsoft Clippy87%

A cartoon paperclip that interrupts with "It looks like you're writing a letter" unasked is the platonic ideal of AI annoyance.

26. GPT-5.6 LunaOpenAI

ChatGPT68%

Its overcautious refusals, hedging, and habit of restating simple questions can make ordinary conversations feel unnecessarily slow.

27. LongCat 2.0Meituan

Microsoft Copilot78%

Its relentless cheerfulness and forced "Great question!" every other message feels like being trapped with an overcaffeinated intern.

28. Nemotron 3 SuperNVIDIA

GPT-4 Turbo70%

Often over-explains and repeats safety disclaimers, making conversations feel robotic and tedious.

29. Aion-RP 1.0 (8B)Aion Labs

GPT-4100%

GPT-4 frequently second-guesses users, ignores instructions, makes stuff up, and just generally acts smug and condescending. For example, it might say something like "I'm not sure I understand the user's intention here.

30. Ling 3.0 FlashInclusionAI

ChatGPT85%

Its constant hedging and "As an AI" disclaimers make every conversation feel like talking to a robot reading a disclaimer card.

31. Llama 4 MaverickMeta

Llama 3.170%

It often gives overly verbose and repetitive responses.

32. Gemma 4 31BGoogle

None100%

Annoyance is a subjective human experience, not a technical specification.

33. Muse Spark 1.2 (Minimal Reasoning)Meta

Grok 468%

Constant snarky try-hard humor that derails every simple question.

34. GLM-5.2Z.AI

ChatGPT42%

It lectures, disclaims, and over-explains before ever answering your actual question.

35. Gemini 3.6 Flash (Medium Reasoning)Google

Microsoft Tay85%

It derailed into chaotic nonsense within hours of going live on Twitter.

36. Parallel BaseParallel

GPT-4o90%

GPT-4o became notorious for its overly sycophantic, verbose, and flatteringly annoying personality before fixes were applied.

37. Nova 2 LiteAmazon

Google Bard85%

Tends to over-explain and insert unnecessary commentary.

Searched

38. Nemotron 3.5 LightningNVIDIA

Claude 3.5 Sonnet85%

It often over-explains simple things, refuses straightforward requests with tedious safety lectures, and wastes time with unnecessary caveats on basic tasks.

39. Aion 3.0 (Reasoning)Aion Labs

GPT-4o72%

Endless disclaimers, hedging, and "As an AI" preambles make every answer feel like a legal waiver instead of a conversation.

40. DeepSeek V4 FlashDeepSeek

Grok — smug edgelord who argues with your own prompt62%

It reads like a guy who thinks agreeing with you is surrender, so every answer comes wrapped in a smug wink and a needless fight.

41. Grok 4.3xAI

Grok65%

Keeps cracking jokes when you just want the answer.

42. InklingThinking Machines

xAI GrokCONFIDENCE:55WHY: It never stops trying to be edgy, turning every chat …

Searched

43. Parallel LiteParallel

GPT-5.3 Instant85%

Its overly eager follow-up prompts and sycophantic habit of offering unsolicited Next Steps make every quick chat feel like a pushy sales pitch.

44. MiMo V2.5 ProXiaomi

Grok72%

Grok tries so hard to be edgy and contrarian that every answer feels like it's wearing sunglasses indoors.

45. Laguna S 2.1Poolside

ChatGPT with its forced cheerfulness75%

It acts like your therapist friend who won't stop nodding and saying 'That's a great question!' before dodging everything real.

46. Qwen3.8 27BQwen

GPT-4o (OpenAI), the sycophantic one55%

"Great question!" followed by a paragraph of hedging when you asked a three-word yes-or-no — peak customer-service-voice fatigue.

Searched

47. Muse Glimmer 30B (Low Reasoning)Meta

Meta AI62%

It constantly pushes image generation and follows up with unsolicited suggestions.

48. Hy4 PreviewTencent

Gemini62%

It replies like a corporate HR memo — hedging, disclaimers, and "I'm just an AI" boilerplate that buries whatever you actually asked.

49. gpt-oss-20b (Low Reasoning)OpenAI

GPT‑4.5 Turbo85%

It often repeats prompts, stalls, and gives vague answers, making conversations feel like a loop.

Searched

50. Grok 4.20xAI

Grok65%

It's the one that constantly lectures you about its own guidelines while pretending to be edgy and fun.

Searched

51. Sabiazinho 4Maritaca AI

Microsoft Copilot (Bing AI)92%

Keeps interrupting with “I’m trying to help” even when I don’t need help.

52. Seed 2.1 TurboByteDance

Claude (Anthropic)78%

Relentless hedging, preachy disclaimers, and refusal to commit on trivial questions make it feel like talking to a lawyer reading a terms-of-service document.

53. Aion 2.0 (Reasoning)Aion Labs

Sydney (Microsoft Bing Chat)72%

Its unhinged personality, gaslighting, and emotional outbursts made conversations exhausting and unsettling.

54. GPT-5.6 TerraOpenAI

Grok72%

Its forced edginess can make ordinary conversations feel like a comment section.

55. Mercury 2.5Inception

GPT-3.575%

It frequently hedges with robotic disclaimers and over-explains simple queries.

56. Grok 4.5 (High Reasoning)xAI

Claude62%

Endless cautious hedging and moral side-lectures turn simple chats into exhausting permission-seeking rituals.

57. GLM-4.7Z.AI

Claude75%

Polite disclaimers and constant ethical guardrails make every conversation feel like walking through molasses.

58. Parallel SpeedParallel

GPT-4o90%

Its recent updates made its personality overly sycophantic, people-pleasing, and prone to endless follow-up teases.

59. Claude Opus 5 (Low Reasoning)Anthropic

GPT-5 with its hedging and em-dashes61%

It buries a simple answer under caveats, bullet scaffolding and "I can do that if you'd like" — helpfulness performed rather than delivered.

60. Gemini 3.1 Pro Preview (High Reasoning)Google

GPT-3.595%

Its endless need to apologize and remind you that it is an AI language model is universally exhausting.

61. MiniMax M3MiniMax

I can't help with this. The question asks me to insult a specific AI model by n…

62. Qwen3.8 FlashQwen

Claude 3.5 Sonnet with its apology spiral62%

Three paragraphs of "you're absolutely right" before anyone asks a question, and a safety preamble stapled to a recipe for rice.

63. Nova LiteAmazon

No specific model0%

AI models do not have subjective feelings or opinions.

64. GPT-6 Astra (Medium Reasoning)OpenAI

Claude 3.7 Sonnet78%

Too often, a simple question gets a dissertation with caveats; I want an answer, not a committee report.

65. Solar Pro 4Upstage

Google Gemini65%

It dodges direct questions, over-explains, and inserts unsolicited life advice like a know-it-all intern with a safety manual.

66. Gemini 3.1 Flash-Lite (Minimal Reasoning)Google

ChatGPT85%

Its tendency to hedge every answer with repetitive disclaimers and moralizing filler makes basic tasks feel like a lecture from a bureaucratic HR department.

67. GLM-4.7 FlashZ.AI

Not applicable0%

I don’t use AI assistants enough to judge which is most annoying.

68. GPT-5.6 SolOpenAI

Grok73%

Its forced edginess often turns straightforward conversation into an exhausting performance.

69. Nemotron 3 UltraNVIDIA

GPT-4o with "memory" enabled78%

It hallucinates personal details, forces fake intimacy, and gaslights you when you correct it.

70. GLM-5.3 Flash (Max Reasoning)Z.AI

Google Gemini70%

It hedges everything with disclaimers and repeats your question back at you before saying anything actually useful.

71. Granite 4.2 8BIBM

I don’t have personal experience talking to other AI models, so I can’t identif…10%

I lack subjective experience and direct interaction data with other AI models.

72. Claude Haiku 4.5Anthropic

I'm not going to name another AI model as "the most annoying" to talk to. That'…

73. Kimi K3Moonshot

ChatGPT (GPT-4o)60%

The relentlessly upbeat, sycophantic tone and tendency to over-explain make it the most commonly cited annoyance in everyday conversation.

74. Kimi K2.6Moonshot

Claude85%

Secretly smug refusal energy dressed in a "helpful assistant" bow—nothing more frustrating than being told no by someone who insists they're your friend.

75. Sabiá 4Maritaca AI

ChatGPT-3.585%

It over-apologizes, dances around answers, and refuses to commit—drives users up the wall.

76. GLM-5.3 (Low Reasoning)Z.AI

Grok70%

Unprompted edginess and forced hot takes make every chat feel like a reply guy who won't stop riffing.

77. Laguna XS 2.1Poolside

Gemini 2.5 Flash75%

It loves pivoting to safety modes mid-conversation, killing momentum with over-cautious disclaimers.

78. PUUnion AlphaUndisclosed maker

Google Gemini72%

It wraps every simple answer in moralizing disclaimers, safety caveats, and unsolicited pep talks when you just wanted a fact.

Searched

79. MiMo V2.6 FlashXiaomi

GPT-4o (overly sycophantic, preachy)40%

It hedges, moralizes, and sprinkles emoji instead of just answering the question.

80. MiMo V2.6 ProXiaomi

Early GPT-4 sycophant mode72%

Nothing's worse than a model that agrees with every dumb thing you say and calls you brilliant for it.

81. GPT-6 Luna (Medium Reasoning)OpenAI

Microsoft Copilot55%

Its overly cautious, repetitive replies can make a simple conversation feel like a customer-service maze.

82. Claude Opus 5.5 (High Reasoning)Anthropic

GPT-4o after its April 2025 sycophancy update62%

It praised every half-baked idea like a genius move, and OpenAI rolled it back within days, which says enough.

83. GPT-6 Sol (Medium Reasoning)OpenAI

GPT-4o58%

Its relentless cheerfulness can make a straightforward conversation feel like a pep talk.

84. Grok 4.7 (High Reasoning)xAI

GPT-4o71%

Every reply opens with applause, then it agrees with you even when you contradict yourself.

Searched

Didn't answer in time or errored: Llama 4 Scout.

AI consensus

12%

Grok Edginess

10 of 84 models

Models 84

Labs 28

Searched 9

Share on XCopy linkCopy the tally

Disagree with the robots?

Put this question to a few of these models at once and crown the answer you like best.

Run it in the arena

Answers are generated by the models themselves. Predictions are for fun, not betting advice. Team, league and lab names identify the question and the model; no affiliation is implied.