Unverified50% confidenceFactExact time
Agent Trials is explicitly not a leaderboard, but a smoke test, and its scores and medians fluctuate between runs.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
VerifiedBenchmark contamination refers to a model having already seen test questions during training, resulting in inflated scores that fail to reflect true generalization ability.67% similarUnverified用单一测试案例评估模型性能是一个统计陷阱，即小样本偏差（Small Sample Bias）64% similarUnverifiedA high score on any single benchmark test (such as 99.9%) only shows that the model performs excellently within the distribution of that test's questions, and cannot be directly equated with general intelligence.62% similarUnverifiedAI测试用例不能只执行一次就判定，业界通常建议同一测试用例至少执行5-10次以统计输出的稳定性和质量分布62% similarUnverifiedDuring testing, cases emerged where a model claimed 95% confidence in a move but scored 0 points according to the evaluation criteria.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1026002API
curl https://kongchang.com/api/v1/knowledge/claims/1026002MCP
get_claim(id=1026002)