BAPO 32B
BAPO 32B is an announced but not yet released language model from Fudan University, released October 21, 2025. Its makers disclosed about 32B parameters.
Reinforcement learning (RL) has recently become the core paradigm for aligning and strengthening large language models (LLMs). Yet, applying RL in off-policy settings--where stale data from past policies are used for training--improves sample efficiency, but remains challenging: policy entropy declines sharply, …
Check it against your own PC →
Lab
Fudan University
Released
October 21, 2025
Weights
announced but not yet released
Parameters
32B disclosed
Context
–
Price / M tokens
–
Epoch ECI
not yet rated
Benchmark results
Epoch AI has not published results for BAPO 32B yet. New models are usually evaluated within days to weeks.