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)→
More from Models
- TIPO v2 Released: MoE-based Prompt Optimization Model for T2I — bdsqlsz · 2026-08-07
- Emad Mostaque: Luna reasoning surpasses GPT-5, top-tier AI will be free in 2 years — jdjohnson · 2026-08-07
- Investor Predicts 10 Trillion Parameter Open Weights Models Before Summer's End — JosephJacks_ · 2026-08-07
- The Era of Model-Harness Co-Design in Applied AI — ypatil125 · 2026-08-07
- vLLM Officially Supports Kimi K3 Deployment, Requires 8x GB300 Minimum — vllm_project · 2026-08-07
- AI Safety Mocked: Over-Refusal, Condescension, and False Triggers — kevinnbass · 2026-08-07