ByteDance's BFS Prover V 2 32B is a chat model exceling at step-level theorem proving for Lean4, with a context window of 131,072 tokens. It achieves state-of-the-art performance, notably scoring 95.08% on the miniF2F test set, a top-tier result.
Input
Output
Context
131K
Max Output
-
Parameters
32.8B
Input Modalities
Output Modalities
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Automatically route workloads to the right model for every task, every time.