Unverified50% confidenceBenchmarkExact time
3,189 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/6/2026
First Seen
Valid until: 1/4/2027
Sources
Related Entities
Related Claims
UnverifiedExperience internalization fine-tuning improved Qwen3-8B-27B's one-shot score from 37.07 to 48.22, while reducing generated tokens from 6.41 million to 570,000 (an 11-fold reduction).76% similarUnverifiedQwen3 27B在Kanban看板应用测试中消耗近87%上下文，一次生成出无bug的成果，支持拖拽、排序、筛选、归档等功能70% similarUnverifiedQwen3 27B achieved a 100% pass rate in the 256K long-context memory retrieval test (needle in a haystack), with all 15 runs being accurate.68% similarUnverifiedQwen3-1.7B's faithfulness is 68% on 2-hop tasks but plummets to 30% on 6-hop tasks, whereas Qwen3-4B remains relatively stable across different hop counts.68% similarUnverifiedQwen3.8-Flash-Next surpasses the Qwen3.8-27B dense model in performance on multiple benchmarks while reducing inference and training overhead.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/980176API
curl https://kongchang.com/api/v1/knowledge/claims/980176MCP
get_claim(id=980176)