How not to flex:
"MAI-Code-1-Flash outperforms Claude Haiku 4.5"
MAI-Code-1-Flash
241–250 of 297 posts
Re: MAI-Code-1-Flash
#242Maybe this will replace raptor-mini as the "free" model on copilot plans?
(but I don't see it at all yet on the student plan, in vscode or the cli)
Re: MAI-Code-1-Flash
#243It's a start and I welcome competition but I don't think I ever used small cloud models like Haiku 4.5. They are cute but for serious coding they tend to waste your expensive time. And this certainly wont bring me back to GitHub Copilot which I cancelled yesterday. GitHub Copilot had competitive pricing until yesterday when they changed from per-request to one of the most expensive per-token quotas. Seriously, take a…
I use larger models to organize work into a topologically sorted task graph and pin smaller models to the tasks depending on the complexity with a larger model evaluating the work and patching where necessary. This uses haiku quite often for routine work. I’m able to do multi hour highly complex work with superior results and a much lower bill as a result by doing this, with a parent orchestrator able to do a massive…
[flagged]
Re: MAI-Code-1-Flash
#244Raw feedback to the team: 1-model looks awesome, 2-The artificially smoothed scrolling on your page feels really bad!
Re: MAI-Code-1-Flash
#245[flagged]
Re: MAI-Code-1-Flash
#246Earlier quoted context omitted.
The $20/month ChatGPT plan that comes with codex is good value. Even just have premium ChatGPT is nice. I get rate limited regularly but it still lets me do most things.
The $100/month is excellent value. I don’t understand how’s that not the default option for all professional developers. Unless people don’t produce any value writing code, like playing around and experimenting with vibe coding, I understand. But if software development is your actual income, and assuming you live in a wealthy country, $100/month is nothing for a tool like Codex.
I don’t live in a wealthy country and my salary isn’t that great, but Anthropic’s 100 USD tier is still worth it for me. I’d probably go with a 50 USD tier if they had one but oh well. I’m also looking at DeepSeek since they permanently lowered their prices and feel like I could probably add the cheaper Codex tier to the list (you really feel the limits with the cheaper Anthropic one though).
Re: MAI-Code-1-Flash
#247So I guess the important link the marketing department forgot is this one: https://docs.github.com/en/copilot/reference/copilot-billing...
Model Input Cached input Output
MAI-Code-1-Flash $0.75 $0.075 $4.50
Comparing to
Claude Haiku 4.5 $1.00 $0.10 $5.00
looks fine.
But they also forgot to include the benchmarks comparing to
GPT-5.4 mini $0.75 $0.075 $4.50
Those would have been helpful.
Re: MAI-Code-1-Flash
#248Earlier quoted context omitted.
I use Gemini 3 Flash, I've seen the Claude Code setups, bullish on Anthropic people are driving up tokens but I am able to produce outcomes with a fraction of the money.
3 Flash is likely rather underrated here. It continues to impress me on few-shot tasks.
GPT-5.4 mini seems noticeably better to me, token cost between Gemini 3 and 3.5 Flash.
Re: MAI-Code-1-Flash
#249Earlier quoted context omitted.
Sorry, what do you mean by "To not own the model is not viable in 2026." I assume I'm misunderstanding you (likely my fault), because the way I read that is that you're saying nobody should currently be using models owned & hosted by companies like OpenAI and Antheopic, while clearly a huge number of people are using those in 2026 despite not owning them.
It's that companies like copilot/cursor are in real trouble if they are in the business of reselling expensive Anthropic tokens
But isn't the current understanding that harness is equally important as model once you get above a certain threshold, so there seems to be room to add value there.
Cursor is potentially about to be acquired by X.ai (i.e. SpaceX), unless this is just some IPO game being played by Musk. They are certainly not just a token reseller since they have their own models in addition to their own vector database approach for code matching.
Re: MAI-Code-1-Flash
#250Huh, according to that model card this is a 137B total parameter model. Performance doesn't seem that good: - MAI-Code-1-Flash (137B-A5B) = 51% on SWE-bench pro - Qwen3.6-35B-A3B = 49.5% on SWE-bench pro ( https://huggingface.co/Qwen/Qwen3.6-35B-A3B ) They benchmark against Claude Haiku but Haiku is not good, it's worse than tiny open models you can run locally or via API at 10% the cost.
While I agree directionally, I'll caveat that "cost per token" != "cost per task". In the case of Qwen3.6 it tends to think 1.6x more than Haiku, so the cost of Haiku on the same tasks tends to only be about double. More detail from comparing their Artificial Analysis metrics: Qwen3.6-35B-A3B vs Claude Haiku 4.5 reasoning mode · AA Intelligence Index v4.0 46.0 ┤ ↖ better — cheaper · smarter · faster │ │ 44.0 ┤ ╭─────…
How did you get that nicely formatted graph and table in your post ?!