Separate SFT+RL from RL only

Hi!

I think that models trained with distillation followed by reinforcement learning, or multiple distillation steps, should have a separate section (or at least an “SFT + RL” indication).

For instance for Qwen2.5-Math-7B, the Sky-T1-7B model is trained with 4-step SFT->RL->SFT->RL vs Oat-Zero and others which are trained in a single RL run.

Wdyt?

(aside: I think the leaderboard would benefit greatly from a verified / unverified section like SWE-bench so that new releases and be added and compared quickly. It would need an easy way to run the full pipeline locally, but I think this would be very useful to the community.)

The issue names no files, tests, or entry points. Start by locating the leaderboard data and model-training metadata, then clarify whether the intended scope is only an SFT + RL indication or also the proposed verified/unverified workflow; done means the distinction and its presentation are agreed and consistently represented.

Written by the indexing model from the issue text.