Unverified50% confidenceBenchmarkExact time
With DeepSeek V4 Pro as the backbone, SwarmRSI achieves a medal rate of 81.8% on MLEBench Lite.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
SwarmRSI: How a Swarm of Research Agents Achieves Recursive Self-Improvement
bilibili熊二等兵10/18/2026
Related Entities
Related Claims
UnverifiedWith DeepSeek V4 Pro as the backbone, SwarmRSI achieves an average score of 74.2 on OpenProblems, exceeding the previous SOTA of 67.1.78% similarUnverifiedWith DeepSeek V4 Pro as the backbone, SwarmRSI's proportion matching SOTA on NatureBench is 21.1 percentage points higher than Claude Code with the same backbone.70% similarVerifiedMLExpert raised the base model's average medal rate on MLE-Bench Lite from 37.9% to 72.7%.64% similarUnverifiedDeepSeek V4.1 claims to achieve 74 on SWE, but the blogger found that this was the best result cherry-picked from multiple tests, with open code testing at 65 and PI testing at 66.63% similarUnverifiedIn the VibeCodeArena leaderboard snapshot, DeepSeek-v4-Flash ranks first with an eval score of 95.3 and an Elo of 1639, but its confidence is labeled Low.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073050API
curl https://kongchang.com/api/v1/knowledge/claims/1073050MCP
get_claim(id=1073050)