Unverified50% confidenceBenchmarkExact time
On HealthBench, post-training Qwen3.5-9B with Rubricon rubrics yields performance 4.5% higher than training with RRD, the strongest alternative synthetic rubric generator.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
Unverified3,189 successful rollouts were collected from Qwen3.8-27B for supervised fine-tuning (imitation learning), and performance stagnated at 47.5%, below the results of two rounds of RL training.69% similarUnverifiedOn the NL2RepoBench benchmark, QwenGyre raised the score from 52.5% to 58.5% in 48 steps, and end-to-end training time was shortened by about 44% compared with the Async scheme.64% similarUnverifiedOn the MedGUIDE benchmark, GUIDER with a Qwen3-14B backbone achieves 82.5 weighted accuracy and 73.5 guideline compliance.64% similarUnverifiedThe paper conducted RL experiments on Qwen3-8B, and after 40 training steps, EnvSched achieved an average score of 48.81 on the three benchmarks BFCL-v3, tau-Bench, and ACEBench-Agent.63% similarUnverifiedUsing QLoRA on A100 and RTX PRO 6000, training speed for Qwen3.5-35B-A3B can be improved by up to 4.1×, and for Qwen3-30B-A3B by up to 3.3×.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114369API
curl https://kongchang.com/api/v1/knowledge/claims/1114369MCP
get_claim(id=1114369)