FRAMEWIREIndonesiaUpdated Sep 29Live wire
0:00 / 0:00

Watch the progress of frontier models in bringing Ancient Rome to life on Arena, from Q4 2025 to now.

Scores for Claude Sonnet 5.5 by AnthropicAI and GPT-6.1 by OpenAI are coming soon. Real-world tasks from our global community of users power the Arena leaderboards. Head to

Arena.aiSep 29104
0:00 / 0:00

I'm testing the operation of the Qwen 3.8 Flash next IQ3

I'm testing the operation of the Qwen 3.8 Flash next IQ3, which I think has completed 90% optimization (making a list of models waiting to be served), and waiting for the Oai Devday announcement. Is this how Noah felt as he nailed the ark?

Serio_aiSep 296
0:00 / 0:00

I tested Bonsai 2 27B

They claim it retains 98.2% performance of the original Qwen 3.8 27B but my results suggest otherwise. It can handle basic tasks, but anything beyond simple HTML gives unusable outputs. Don't get me wrong, it's already impressive compressing a 5.9GB model

Red StaplerSep 29
0:00 / 0:00

Qwen 3.8 Next Flash + OMP

ONE SHOT - Full blown 3d scene editor. What is this sorcery o_O Assets made locally by HY3d2.1 + Qwen next + Qwen Image It's too much for me ;) I need to sit and think. ps. You can also test/walk on the stage

GabuSep 2912