Unverified50% confidenceBenchmarkExact time
After RL post-training, the small model's accuracy improves from 4% to 45% (pass@1).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/6/2026
First Seen
Valid until: 1/4/2027
Sources
Related Entities
Cite This Claim
Stable URI
https://kongchang.com/claim/982182API
curl https://kongchang.com/api/v1/knowledge/claims/982182MCP
get_claim(id=982182)