Can It Code?
youtube.com · Sep 30
Two new models in two days: Claude Sonnet 5.5 from Anthropic and GPT-6.1 Sol from OpenAI. Sonnet is ahead of Opus on Terminal-Bench, and both new models cost $2 per million input tokens and $10 per million output tokens, half the price of Claude Opus 5.5. So I put all three on…
Can It Code?
youtube.com · Oct 3
Two days ago GPT-6.1 Sol lost badly to Opus 5.5, but it was also way cheaper, so many of you asked: what if Sol gets the same budget? So I gave both models the same API budget, their top settings, no limit on agents, and two games to build from scratch in Blender and Godot: NEON…
Code Bear
youtube.com · Sep 30
Same prompt, same model, five times. The only thing that changes is how hard GPT-6.1 Sol is allowed to think: low, medium, high, extra high and ultra (in Codex). Each run had to build a deep-sea research station in Blender from one Python script. No downloaded models, no…
Stefan 3D AI
youtube.com · Oct 7
I challenged GPT-6.1 to build a third-person horror game.
The setting is a swamp full of Slavic mythology creatures. Before I even got to play the result, I ran into a real horror story with the new $500 Ultrafast plan. In the video I show the preparation, what the agent…
Matt Johnston | AI Engineer
youtube.com · Sep 29
Follow @mattjohnston_ai
GPT-6.1 Sol showed up at OpenAI Dev Day and the claim was near-Astra, at a fifth of the price. I ran it through the full Stonelabs proving ground the day it shipped. Nine tests, live.
Halo is a 98. The phone case is a 95. The sales page is a 98, right…
Devsplainers
youtube.com · Oct 2
GPT-6.1 Sol got one hour, a Remotion project and a $5 OpenRouter budget to make a video for this channel. This is the video it made, uncut, followed by my verdict.
Episode 1 of AI's Next Top Model. Every new model gets the same brief and the same tools, then picks its own…
Emil Nielsen
youtube.com · Sep 29
In this video, I put GPT 6.1 Sol to the test by trying to recreate WoW Forever in a single prompt. I compare the results with GPT 6 Astra, Opus 5.5, and Sonnet 5.5 to see how they stack up at game development.
Timestamps:
00:00 Intro
00:39 GPT 6 Astra (xhigh)
02:49 GPT 6.1 Sol…
Venelin Valkov
youtube.com · Oct 3
GPT 6.1 Sol is "Near-Astra" intelligence for a much cheaper price, is it really? Can you replace Opus 5.5 for a cheaper price and better outputs? Let's try it out!
👍 Don't Forget to Like, Comment, and Subscribe for More Tutorials!
Join this channel to get access to the perks…
