Verified75% confidenceBenchmarkExact time
MLExpert raised the base model's average medal rate on MLE-Bench Lite from 37.9% to 72.7%.
3
Sources
75%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedIn the segment where gains exceeded +30%, average model predictions ranged from 27.3% for Claude Opus 5.5 to 61.6% for GPT-5.4 mini, while the actual rise rate was 42.8%.64% similarUnverifiedAccording to the official DeepSeek model card, the 1017 version's score on HLE without tools rose from 36.8 to 42.6.62% similarUnverifiedIn the initial publicly released SWE-bench results, GPT-4's resolution rate was only approximately 1.7%, Devin claimed to reach 13.86%, and SWE-agent reached 12.5%.60% similarUnverifiedHMA achieved an any-medal rate of 78.2% on the MLE-bench benchmark (covering 75 Kaggle tasks), setting a new state-of-the-art (SOTA).60% similarUnverifiedTEMPEST outperforms the best classical model by 17.9 percentage points and the strongest triplet-loss baseline by 58.4 percentage points.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041826API
curl https://kongchang.com/api/v1/knowledge/claims/1041826MCP
get_claim(id=1041826)