35B Beats 1.6T: BigBang Model Achieves SOTA via Self-Evolving Synthetic Data

ChengleiSi · x · 2026-08-07

The research team introduced BigBang-V1, based on Qwen3.6-35B-A3B. Post-trained entirely on synthetic data, it outperforms the 1.6T parameter DeepSeek V4 Pro Preview on four frontier benchmarks.

The core breakthrough lies in data-layer Recursive Self-Improvement (RSI): the AI autonomously rewrites its data-generation code, using real-world gains to steer subsequent generations. Grounded in verifiable frontier tasks, this method utilizes a generator-critic loop to continuously expose capability gaps and produce high-quality data, achieving SOTA performance at a fraction of the scale.

Related event: BigBang-V1 35B Model Outperforms Trillion-Parameter Giants(2 posts)→

Original post →

More from Models

Models channel →