Unverified50% confidenceBenchmarkExact time
During exploiter training, the win rate against the step-43,800 snapshot was about 85%; in its winning games, the cs count was 67 to 9.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/2/2026
First Seen
Valid until: 1/31/2027
Sources
Related Entities
Related Claims
UnverifiedAt recording time the main agent's win rate against the fixed opponent was about 81% to 83% (plateauing from around step 39,000), leading in cs 48 to 17, and it almost never attacks a full-health turret.73% similarUnverifiedIn the strictly comparable experiment with fifteen players and three impostors in the sixth league, the trained network's crew win rate over 300 rounds was 93.3%, while gpt-oss under the dialogue+intuition format won 16 of 20 rounds (80%), with a one-sided Fisher exact test p = 0.052.67% similarVerified如果一个10步操作中每步准确率为95%，整体成功率仅约60%67% similarVerifiedIn a reproduction experiment training for 40 epochs on CIFAR-10, plain-56 achieved a training accuracy of 84.0% and plain-20 achieved a training accuracy of 95.1%, even though plain-56's parameter count (853,018) is approximately three times that of plain-20 (269,722).67% similarUnverifiedThe 62% improvement is a result at the decoding stage, not an end-to-end training speedup ratio.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125548API
curl https://kongchang.com/api/v1/knowledge/claims/1125548MCP
get_claim(id=1125548)