Hacker News

points by seizethecheese 3 days ago | 0 comments

Speaking of arena comparisons of K3.1 and DS4.1-Flash, we're spinning one up that's more relevant than design, I think: https://agentduel.com/leaderboard

Here, DS4.1-Flash and K3.1 are basically tied, with K3.1 being slower and more expensive. Big error bars, though.

Even with error bars, DS4.1-flash is clearly an impressive model.

[–] reissbaker 3 days ago

If your benchmark puts DS4.1-Flash at the same tier as K3 or K3.1, I'm sorry to say your benchmark is broken. It really isn't, as much as I wish it was.

[–] seizethecheese 3 days ago

We allow early voting. This is against what most arenas do, but is on purpose. If the model is faster to do simple stuff, it should be chosen. In this sense, DS4.1-Flash is better on many tasks.

You can remove early voting from leaderboard and they are no longer the same.

[–] purerandomness 3 days ago

At the point where I choose an expensive model like Kimi 3.1, speed doesn't matter, at all.

Usually, it's because all else failed, and I have to resort to burning Tokens with more expensive/better models, so a few minutes here and there really should not matter.

[–] seizethecheese 3 days ago

I think you’re alone to think time for task completion doesn’t matter

[–] rocho 3 days ago

But his point is that the faster models could _not_ complete the task satisfactorily.

I've seen this myself too: DeepSeek 4.1 Flash is really good and incredibly cheap at constrained implementations, searches, etc. However, frequently the implementations don't take into account all possible cases they should cover. Then I'm either forced to step in and steer it very precisely, or have a heavier model review and provide detailed feedback. I've had good success with this mixed workflow using GPT 6.1 Sol as reviewer. Then my work focuses mostly at the beginning (architecture, goals, constraints), and at the end (final review or very quick intermediate reviews). I'm not aware of benchmarks that simulate this kind of mixed workflow with different models.

[–] nostrebored 3 days ago

But how do you verify a fair or representative distribution of complexity?

[–] seizethecheese 3 days ago

We validate people are doing real work using LLM judges.

[–] haizhung 3 days ago

I tried both of them for agentic coding and didn’t feel like K3 was adding so much benefit to justify its almost 10x price (on the modem provider I’m on).

In fact, I barely see a difference between the results at all. The models being tied smells correct to me.

I didn’t try 3.1 yet, though.

[–] eunos 3 days ago

It's quite hilarious that kimi K3.1 was competitive against Opus 5.5 and a bit lagging against DS V4.1F. While DS struggled against Opus