I don't know how the coding benchmarks are computed but this model, on its own and outside of agentic loops, definitely doesn't compare to e.g. Qwen3 Coder. I might still try that for fun, just to see how it performs given a feedback loop.
On math questions, though, beside a marked tendency towards rambling thinking, it's just plain implausibly good for a 1.5B model. This is probably just rote learning, though. Otherwise this might well be a breakthrough.
While impressive that the output isn't completely undecipherable, my real-world queries for SpringBoot project with most popular libraries don't compare so favorably to their benchmarks against Qwen3 32B, which I also run regularly (a 4bit quantized version of). Explaining tasks break completely and often.
Used their recommended temperature, top_k, top_p and so on settings
I'm pretty sure that this is some kind of scientific achievement that I do not fully understand but the real world use cases for this model seem to be very limited.
I gave it two tasks. "Create a new and original story in 500 words" and "Write a Python console game". Both of those resulted in an endless loop with the model repeating itself
I'm honest. Given that a 1B Granite nano model has only little problems (word count) with such tasks and given that VibeThinker is announced as a programming model it's disappointing to see a 1.6B model fail multiple times.
So during the final they try to ensure the model doesn't get the right answer every time, but only 50% of time, so as to avoid killing all variability-- very sensible, and then they compute a measure of this, take the negative exponential of this measure and then they scale the advantage by this.
So a question matters in proportion to the variability of the answers. Isn't this more curriculum learning stuff than actually suppressing things that don't vary enough?
Basically focusing on questions that are still hard instead of trying to push the probability of problem it's often able to solve to 99.99%?
Also very reasonable, but this isn't how they describe it. Instead, from their description I would think they're sort of forcing entropy to be high somehow.
I think the way I'd have titled it would be something like "Dynamic curricula to preserve model entropy".
7 comments
[ 13.1 ms ] story [ 596 ms ] threadIs this hosted online somewhere so I can try it out?
On math questions, though, beside a marked tendency towards rambling thinking, it's just plain implausibly good for a 1.5B model. This is probably just rote learning, though. Otherwise this might well be a breakthrough.
Used their recommended temperature, top_k, top_p and so on settings
I gave it two tasks. "Create a new and original story in 500 words" and "Write a Python console game". Both of those resulted in an endless loop with the model repeating itself
I'm honest. Given that a 1B Granite nano model has only little problems (word count) with such tasks and given that VibeThinker is announced as a programming model it's disappointing to see a 1.6B model fail multiple times.
So during the final they try to ensure the model doesn't get the right answer every time, but only 50% of time, so as to avoid killing all variability-- very sensible, and then they compute a measure of this, take the negative exponential of this measure and then they scale the advantage by this.
So a question matters in proportion to the variability of the answers. Isn't this more curriculum learning stuff than actually suppressing things that don't vary enough?
Basically focusing on questions that are still hard instead of trying to push the probability of problem it's often able to solve to 99.99%?
Also very reasonable, but this isn't how they describe it. Instead, from their description I would think they're sort of forcing entropy to be high somehow.
I think the way I'd have titled it would be something like "Dynamic curricula to preserve model entropy".