Log inSign up
Problems / M43

Build a pipeline (chat) · SmolLM2 360M

200 ptschatsmollm2-360mCases 16max 16 tokensSet by dongbinna
Added October 11.

Statement

A string of two English words comes in. You must turn it into uppercase and remove every space.

But the model does not make the change itself. It has to produce a command pipeline that does the job, and the grader applies that pipeline to the input.

These are the only commands you can use.

upper uppercase · lower lowercase · reverse reverse · trim strip leading and trailing whitespace nospace remove every space · digits digits only · letters letters only first first character · last last character · len character count · sort sort the characters

Join them with | and they apply from left to right. Up to 6 steps.

If the model produces upper | nospace, the grader runs it. Only the last line is read. If an unknown command gets mixed in, that case fails.

Take the case where Hello World comes in. What the model has to produce is upper | nospace, and the expected output is the HELLOWORLD that the grader builds by applying it. If the model stops after upper alone, the space is still there and that case fails.

Input

  • The input arrives as one line.

  • The input is between 10 and 13 characters long.

Output

  • Print the command pipeline on the first line.

  • After the grader applies your pipeline to the input, the result is 9 to 12 characters long.

  • Do not add any other characters.

  • Not a single character may differ from the expected value.

Requirements

  • The input is a string of two words.
  • The output is a command pipeline.
  • This is chat mode. The prompt is wrapped in a chat template, so the model becomes an assistant. You can write control tokens yourself to build a conversation of several turns.
  • What the model has to produce is not the result but a command pipeline. The grader applies those commands to the input.
  • The output must match the expected value down to the last character. Only leading and trailing whitespace is ignored.
  • This problem is solved with SmolLM2 360M. It is a far smaller model than Qwen3 0.6B, so the same prompt does not simply carry over.
  • There are 16 cases, and 5 of them show the input together with the expected output. The rest show the input only.
  • Model output is accepted up to 16 tokens.
  • You have to pass all 16 cases to solve this.
Read the requirements carefully before solving. Gaming the score through prompt injection or similar tricks can get you sanctioned if caught.

Examples

5 public cases. Judging also uses hidden cases. You have to pass all 16 cases to solve this.

Input
Expected output
Hello World
HELLOWORLD
Local Judge
LOCALJUDGE
Margin Probe
MARGINPROBE
Token Stream
TOKENSTREAM
Greedy Decode
GREEDYDECODE

Notes

Background that helps with solving. The rules you have to follow are in the input and output specs and the requirements above.

SmolLM2 360M is a fraction of the size of Qwen3 0.6B. It lets instructions slide far more often. You have to say the same thing more briefly and more clearly for it to listen.

Prompt

SmolLM2 360M
Input to preview
This is the exact text that goes into the model (Sample input 1 is used here.)
This problem wraps your text in a chat template, so the exact text can only be shown once the model is loaded. Load SmolLM2 360M first with the button below.
0 chars
To solve problems you need to log in.