AA has limited 1017 benchmarks so some terras versus 1017 Max:
max - 3 points smarter, 50% more expensive
xhigh - same score, 25% cheaper
high - 1 point dumber, 50% cheaper
Yes, V4.1 Flash 1017 is my daily driver cloud model. Copes fine with what I'd consider difficult brownfield development, like fixing bugs in vLLM prompt cache and coming up with small/sane overlay patches for them. Maybe it's disappointing for people who want to one-shot a game or website from a single prompt; I haven't tried that.
It's nice that their peak-rate hours end quite early in the day UK time.
You can do real world development with weaker models than Deepseek Flash.
I still use SOTA for the main model though, but also I'm perfectly aware it's mostly out of FOMO.
Deepseek is more than enough for default subagents though. Any well defined and verifiable task and there's absolutely zero difference between SOTA and good-enough models. Used to be just speed, but Deepseek is fast.
I have same the same FOMO to use SOTA model for all planning and brainstorming session. However, I’m unsure how do you bring deepseek for subagent task. Could you describe your workflow?
For myself, using Codex, I always have to explicitly tell codex to use Luna with high reasoning for smaller, bit size tasks.
AA has limited 1017 benchmarks so some terras versus 1017 Max: max - 3 points smarter, 50% more expensive xhigh - same score, 25% cheaper high - 1 point dumber, 50% cheaper
Do people use deepseek for real world development or just for building experimental large projects?
Yes, V4.1 Flash 1017 is my daily driver cloud model. Copes fine with what I'd consider difficult brownfield development, like fixing bugs in vLLM prompt cache and coming up with small/sane overlay patches for them. Maybe it's disappointing for people who want to one-shot a game or website from a single prompt; I haven't tried that.
It's nice that their peak-rate hours end quite early in the day UK time.
I use it at work. It's dirt cheap, blazing fast, and is more than enough for most coding work.
If you live in a country with a weak currency, DeepSeek models are definitely a godsend.
You can do real world development with weaker models than Deepseek Flash.
I still use SOTA for the main model though, but also I'm perfectly aware it's mostly out of FOMO.
Deepseek is more than enough for default subagents though. Any well defined and verifiable task and there's absolutely zero difference between SOTA and good-enough models. Used to be just speed, but Deepseek is fast.
I have same the same FOMO to use SOTA model for all planning and brainstorming session. However, I’m unsure how do you bring deepseek for subagent task. Could you describe your workflow?
For myself, using Codex, I always have to explicitly tell codex to use Luna with high reasoning for smaller, bit size tasks.
1 reply →
It's only a little better than Deepseek with Max effort in benchmarks. Doesn't bode too well for 6.1 Luna.