Unverified50% confidenceBenchmarkExact time
The model's F1 score is 72%, and the data has a severe class imbalance with a ratio of 89:11.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/29/2026
First Seen
Valid until: 11/27/2026
Sources
Related Entities
Related Claims
Unverified在评估阶段对候选关系标签进行随机打乱后，该模型的F1从37%骤降到14%65% similarUnverifiedOn the Terminal Bench 2.1 benchmark, Ultra mode approaches 92%, surpassing competitors' performance of 88%.62% similarUnverifiedBenchmark overfitting is a core problem in current large model evaluation; some models achieve pass rates above 90% on HumanEval but perform far below expectations in real codebases.60% similarUnverifiedSome models have already surpassed 90% of the human average score on MMLU, causing their discriminative power to drop sharply.59% similarUnverified当所有模型在某评测上都能拿90分时该评测就应退场，即基准饱和现象59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/821047API
curl https://kongchang.com/api/v1/knowledge/claims/821047MCP
get_claim(id=821047)