codename-discussion

[tawdry pendant]

I'm sure logs can verify

[barren kiln]

Sure man

[gleaming current]

Hello

<@&1349916362595635286>

GWEEN BEAN💀💀💀💀💀💀💀💀💀💀💀💀💀

[sturdy kestrel]

💀

🥀

we ar cooked

[fair basin]

Hey guys where i can create ai video here?

[lethal cypress]

Only on website

[umbral niche]

The Video Arena is currently accessible through: https://arena.ai/video. More information on how to use Video Arena can be found in this article.

[neon rover]

god I'm just getting spammed with tetra models right now and they all... just suck really badly

it's killing basically every matchup by default

[civic bolt]

we all cooked

[gloomy pelican]

Heey everyone

Is this model still available in this arena? Like: gpt5.5 high and 5.4 high.

[distant nimbus]

yes, but not direct chat. If u get luck u can only get this in battle mode. Reason is cost

[upbeat mirage]

i tried it (gpt-5.5-[x]high) out in battle, it sucks, when trying to create an engine for jungle chess in Rust

opus is likely better

(the Rust engine of gpt was… blargh)

but the GUI was great (it one-shotted a beautiful and functional interface, in Rust)

[neon rover]

ok, the Tetra thing is getting genuinely ridiculous. I've had Tetra 5/5 times across two different sessions now

Is there a way to blocklist models by a regex pattern or something? lol

[candid haven]

are you getting tetra for the same prompt, or similar prompts? or entirely different from each other?

[neon rover]

Completely different prompts across a wide range of themes/tasks

[carmine jacinth]

Personality kind of feels like GPT or Gemini, guessing Gemini as it’s coming out next week

[green plaza]

recraft-v4.1-utility

"Special Ed classroom yearbook group picture"

And second is from Recraft V4

Notice difference

Another from recraft-v4.1-utility

[median lance]

Hello eveybody, I have a question... I have always limitation now. I only can do 2 or 3 battles per day. Is it normal ?

[astral musk]

Are you referring to Video Arena?

[hard badger]

wow

dude

[remote nymph]

whatever openhard-1.0-search-nocot-0506 is supposed to be

name sounds like macrohard which elon musk announced earlier this year

also openhard's whole answer is hallucinated the sources do not match its response at all

[candid surge]

God Elon is such a manchild. Macrohard isn't even original

[safe drift]

Has anyone ran into this Gemini 3.0 flash model that people are talking about I guess that’s different than the Gemini 3 flash model that’s on the leaderboard? I saw people saying it’s actually 3.5 lol I can’t keep up with these rumors

[vagrant scroll]

I got luxor-alt

[candid haven]

the gemini 3 flash i got in battle mode actually beat opus 4.7 thinking on a task lol. it's really powerful and quick.

[upbeat mirage]

yeah, but can it beat Opus-4.6-thinking ?

(which still is better than 4.7)

and can it beat recent GPT?

[green plaza]

Bubble from bfdi

By ellsworth I found

[crimson orchid]

3 in a row wow

[frosty mantle]

Kiravel is solid

[vagrant scroll]

Luxor

What is luxor

[agile furnace]

huh

hmm

[vagrant scroll]

I got Luxor and Luxor alt

[agile furnace]

are they good

[vagrant scroll]

Luxor is okay

And Luxor alt as well

[agile furnace]

probably a google model

[vagrant scroll]

O

[agile furnace]

You should do more test

[vagrant scroll]

I got luxor 1 time and Luxor alt 1 time

I also got hyena

[agile furnace]

does response sound like gemini

or claude

[vagrant scroll]

It sounds a little claude like

Similar to claude sonnet 4.5

[agile furnace]

Hmmm!

[agile furnace]

ask it about tawian

taiwan

I want to know if that's an chinese model

[vagrant scroll]

Ok

[vagrant scroll]

Alr bro arena just teasing me

[agile furnace]

damn you got gpt 5.5 xhigh

really rare

[vagrant scroll]

Maybot 26

[upbeat mirage]

is it better for vibecoding than Opus-4.6-thinking?

(when writing engines for niche boardgames)

[neon rover]

luxor has been extremely spammy with emoji in my experience so far

I don't usually do more than 1-2 prompts per battle so I don't have a ton of responses from it

[prime quiver]

what models is ellsworth

nano banana 2 pro or nano banana 3?

[carmine jacinth]

I got it when ironically chatting about something relating to ancient Egypt

[vagrant scroll]

Nice

[full pendant]

nano banana 3 is better than 2.

[gritty mural]

I've just witnessed a battle between korin and gpt 5.5 xhigh. Haven't found anything here when searching for korin, does anyone know something?

[tranquil field]

Excuse me Because I'm still learning how to use it The required number of tokens has been used. Please start a new chat to continue What should I do next? I just need to start a new chat, right? Can't I restore the chat history? Thank you.

[astral musk]

Yeah you'll want to start a new chat session. These chat sessions are going to have context limits which you can learn about here: https://help.arena.ai/articles/3975292349-arena-troubleshooting-session-token-limits.

Can't I restore the chat history?
Sorry to say we do not have this feature.

[tranquil field]

Thank you very much.

[trim grotto]

when pasting my script in ai chat it gives me this error Trace ID: d1487078-769f

[astral musk]

Would you mind sharing this in #1417174113092374689 ?

[carmine jacinth]

is an unlogoed muse-spark model secretly gemini 3.2/3.5

[lost hemlock]

new model "kyrin" in code arena

[lost hemlock]

and "kymir" too

[gritty mural]

Kymir flip flops a lot for me in code suggestions. While the presentation is convincing, I do not trust its output very much.

[bitter plaza]

What's this new model? It's pretty good for images

[tranquil pewter]

Got 'flashfennel' for a single image edit test, not bad

[frosty mantle]

Maylynx's visual understanding is solid.

[tranquil pewter]

Was hit with Kymir twice in coding, did well the first time but was a flop the second.

[green plaza]

boulders falling down the hill - allosaurus

Have you seen allosaurus

[lost hemlock]

maylynx-alpha

new model

[tranquil pewter]

Just got this one too in image edit

[river kettle]

blue-crab

[stark jasper]

Nice picture

[river kettle]

ellsworth

[lost hemlock]

"u2-preview" in text arena

what do u think about ts model?

[lost hemlock]

and "mizar-beta"

[cunning parcel]

hi

[marble flame]

New Claude Model!!

It made an apple clone but with a phone named nova https://019e5086-8c92-7766-8864-e19c1052cf39.arena.site/

cuz it says

it doesnt want to copy

[restive vapor]

probably a chinese distill

[marble flame]

the phone and other models are good

[marble flame]

I think it is a claude model

look at the result

another here and it gives heavy claude vibes https://019e507b-ebdd-788f-9b19-831faf618d28.arena.site/

All I typed was "luxury"

This could be a new sonnet model

or opus

[restive vapor]

anthropic has never done pre-release testing on arena before, it would be weird for them to do it now

[marble flame]

oh

but the model keeps saying its claude 😭

also

QWEN 3.7 MAX IS SO GOATED

[restive vapor]

some Chinese models can do that

[marble flame]

qwen 3.7 kinda beating opus in frontend

ngl

[restive vapor]

tested that yesterday and i got a loopy mess, at least it got itself out of its loop (qwen 3.5 is infamous for entering infinite loops)

[marble flame]

I honestly dont

[restive vapor]

well that's because you're coding, qwen and hard world knowledge questions don't mix well

[ionic plume]

u haven't seen mimo v2.5 pro

[upbeat mirage]

this server seriously needs a honeypot against this bot plague..

(a digital venus fly trap)

[upbeat mirage]

is Mimo better in coding than all other AI models?

[visual sun]

frontend maybe

[green plaza]

What is king-crab

Prompt" Lost Media video about The Lost Game of Talking Pineapple

[ionic plume]

not entirely; sometimes it goes into a CoT that last 10 minutes

[upbeat mirage]

ok, ty for info
btw, i just encountered dark-matter
seems to be a decent model

unfortunately, it doesn't tell, what it is or who build it

[ionic plume]

hmmm, talk to it about taiwan and tianan square

[candid surge]

maybe its gemini 3.5 pro

[upbeat mirage]

unfortunately, the showstopping-bug resurfaced for me (in battle mode)
but adding web-search re-enables access, for some reason

[upbeat mirage]

that would be the first time, a google model hid its identity

[candid surge]

would it? well, nano banana was a codenamed model…

[upbeat mirage]

i mean, for text models

if you asked any gemini model, they always admit having been created by google

(even for experimental versions, which only were in arena-battle, iirc/afaik)

[river kettle]

king-crab (Grok)

[tranquil pewter]

Just got king-crab too in t2i, REALLY good for my test

[river kettle]

snow-crab

[woeful junco]

Now thats insane

[green plaza]

@woeful junco

[keen bridge]

Must be another Nano Banana model

[green plaza]

@keen bridge well gemini said it doesn't have SynthID

[quaint aspen]

$now?

[zenith shore]

Snow crab is Reve 2.0?

[flat root]

Kelly
-> Image Model
-> Editor: OpenAI (almost certain, it gave exactly the same result as gpt-image-2 but had some mistakes on text and image)
-> Gpt-image-2-fast-alpha (whatever it's called, it's a cheap version of gpt-image-2)

[tranquil pewter]

"caudipteryx" appeared for me on t2i.

[river kettle]

kelly

[tranquil pewter]

It was mentioned a while back but I got rising-sun on Search battle and yeah woof is it bad

[green plaza]

@river kettle what was the prompt, so I could try it if I get a codename model image

Btw, have you heard of mai image 2.5

[pulsar shoal]

anyone know about phantom_brush ? getting it a lot in the battle ...

[pulsar shoal]

from my first tries its really good !

[pulsar shoal]

hello Kjei i am getting good result with that prompt : create infographic stating your model name and creator and model stat overview

[candid surge]

I got phantom_brush once and now I'm only getting Flux and wan 🤢

[fierce heart]

runway_gen sucks
"kelly" isn't good at all either

[river kettle]

Just ask for a "detailed infographic" and list everything you want to know. mai 2.5 is nothing special.

[blissful frigate]

Sooo, it turns out that this was a new iteration of Qwen 3.7 Max..

[marble flame]

Really? Where's the link for the post

[blissful frigate]

I saw it on another server.

[marble flame]

Wow it was REALLY good