Deepseek-R1 has been a hot topic in the past days. We've been working on something pretty similar. Figure 1 shows a model response from a model that was trained a week ago (two days before the drop of R1), and you can see pretty similar behaviors of self-correcting. This was an extension of our works on OLV (Olaf-With-Verification).
(link to model is as the bottom of the page)

Now, with Deepseek-R1 being public and our work outdated, we've raced to bring the first Korean re-implementation of R1. Earlier this month, in our paper (Ko et al., 2025), we discussed a three-step generation process where we use models to initially understand (or solve) in English and then translate the results into Korean. We found this applicable to R1 as well since it also responds in two steps: <think> and <solution>. Most of the solving is actually done in the <think> step, which is followed by a <solution> step that restates the answer for better readability. Accordingly, in our implementation of Ko-R1, we first make our model think in English and respond in Korean.
Here is a sample response:
Q: $2^8=4^x$일 때, $x$의 값은 얼마입니까?
Response by ko-r1-preview-1.5B:
<think>
Okay, so I need to solve the equation 2^8 = 4^x and find the value of x. Let me think about how to approach this step by step. \\n\\nFirst, I remember that when dealing with exponential equations, it's often helpful to express both sides of the equation with the same base if possible. That way, I can set the exponents equal to each other because if a^b = c^d, then b must equal d if a and c are the same. So, let's see if I can rewrite 4 as a power of 2. Since 4 is 2 squared, right? Because 2 times 2 is 4. So, 4 is 2^2.\\n\\nSo substituting that into the original equation, we have:\\n\\n2^8 = (2^2)^x\\n\\nNow, using the exponentiation rule (a^m)^n = a^(m*n), which means multiplying the exponents. Applying that here, the right side becomes 2^(2*x). So now the equation is:\\n\\n2^8 = 2^(2x)\\n\\nSince the bases are the same (both are powers of 2), their exponents must be equal for the equality to hold. Therefore, I can set the exponents equal to each other:\\n\\n8 = 2x\\n\\nTo solve for x, I just divide both sides by 2:\\n\\nx = 8 / 2\\nx = 4\\n\\nWait, let me check that again. If x is 4, then 4^4 would be 256, and 2^8 is also 256. Yeah, that works out. But maybe there's another way to verify?\\n\\nAlternatively, I could take logarithms on both sides. Let's try that method to confirm. Taking the natural log or common log of both sides. Let's use natural logs for this example.\\n\\nTaking ln of both sides:\\n\\nln(2^8) = ln(4^x)\\n\\nUsing the logarithm property that ln(a^b) = b*ln(a):\\n\\n8*ln(2) = x*ln(4)\\n\\nThen solving for x:\\n\\nx = (8*ln(2)) / ln(4)\\n\\nBut since 4 is 2^2, ln(4) is ln(2^2) = 2*ln(2). Substituting back in:\\n\\nx = (8*ln(2)) / (2*ln(2)) = 8/2 = 4\\n\\nSame result. So that confirms it. Both methods give x = 4. \\n\\nAnother way to look at it: Maybe converting both numbers to base 10? Although that might not be necessary here. Let's see. 2^8 is 256, and 4^x. If I compute 4^x until I reach 256, starting from x=1: 4, 16, 64, 256. So that's 4^4=256. Yep, so x=4. \\n\\nI guess all these different approaches—expressing both sides with the same base, taking logarithms, and iterative checking—all lead to the same answer. It seems pretty straightforward once you recognize that 4 is a power of 2. The key was to express everything in terms of the same base before equating the exponents. \\n\\nJust to recap: Original equation is 2^8 equals 4^x. Express 4 as 2^2, substitute into the equation, simplify using exponent rules, set exponents equal, solve for x. All steps check out, and verifying through multiple methods gives confidence in the solution.
</think>
<solution>\\n\\\\(2^8 = 4^x\\\\)을 풀기 위해, 우리는 양쪽을 같은 밑으로 표현합니다. \\\\(4\\\\)를 \\\\(2^2\\\\)로 다시 씁니다:\\n\\n\\\\[\\n2^8 = (2^2)^x\\n\\\\]\\n\\n지수 법칙 \\\\((a^m)^n = a^{mn}\\\\)을 사용하여 오른쪽을 단순화하면:\\n\\n\\\\[\\n2^8 = 2^{2x}\\n\\\\]\\n\\n밑이 같으므로 지수는 같아야 합니다:\\n\\n\\\\[\\n8 = 2x\\n\\\\]\\n\\n\\\\(x\\\\)를 구하면:\\n\\n\\\\[\\nx = \\\\frac{8}{2} = 4\\n\\\\]\\n\\n검증:\\n- \\\\(4^4 = 256\\\\)이고 \\\\(2^8 = 256\\\\)이므로 해가 맞음을 확인할 수 있습니다.\\n- 로그를 사용한 검증도 결과를 확인합니다.\\n\\n따라서, \\\\(x\\\\)의 값은 \\\\(\\\\boxed{4}\\\\)입니다.
</solution>
The biggest issue is performance, right? We evaluated on three subsets of HRM8K: GSM8K, Math, and Omni Math. I am planning a few updates on the KSM subset, so it has been left out. I will try to push the updates soon. I use the following setting for evaluation:
You can see the models outperforming models of similar size and even those that are way bigger. It only struggles in GSM8K, which is similar to findings from Chen et al., 2025, where these o1-like LLMs trained to generate longer sequences tend to overthink in easier questions.

We release the model (1.5B) and evaluation result files.
Bigger and better models will come soon.
Enjoy the model here -> [Link to Model]