2 September 2026
Qwen model trained on 1,928 work tasks, performance improved 70%
First reported
TLDR AI ran this on .
- Mercor and SkyRL companies took Qwen3.5-397B-A17B model, a large language model with 397 billion parameters, and trained it on 1,928 different knowledge work tasks like analysis and writing.
- The trained model's APEX-Agents Pass@1 score, a measure of how often it completes tasks correctly on first try, increased by 70 percent.
