Indic-Task Gains and Regressions after Reinforcement Learning.

We run reinforcement learning (RL) with GRPO across four environments, starting from a supervised fine-tuned 30B-A3B mixture-of-experts model covering English and eight Indic languages. We compare the model before and after RL across 35 benchmarks in one evaluation campaign. MATH improves by 36.07 points, and most Indic benchmarks also improve. Yet passage answering falls by 19.32 F1 points on XQuAD-Indic and 8.64 on IndicQA, while English XQuAD gains 11.71 F1 under the same grading method. A second RL run from the same supervised initialization adds an Indic environment together with language and repetition rewards. Compared with the released model, it improves both passage-answering and instruction-following benchmarks while preserving MATH performance. However, it loses ground on reasoning and coding benchmarks. Several training choices changed together, so we cannot isolate the effect of any one reward term. Script compliance remains unresolved: adding a language reward did not ensure use of the requested script. Passage answering and script compliance therefore need direct evaluation, even when other benchmark scores improve.