Unverified50% confidenceFactExact time
The accuracy of retrieval models is typically evaluated on standard benchmarks such as BEIR and MTEB.
1
Sources
50%
Confidence
Long-term
Relevance
10/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEvaluating actual model performance requires reference to independent benchmark results, such as MMLU, HumanEval, and MT-Bench.74% similarUnverified数据标注评估考核中常见的质量指标包括标注者间一致性（IAA）和与黄金标准的偏差72% similarUnverifiedExperiments show that the gated objective achieved the highest average accuracy on both datasets, verifying that objective reliability and evaluation priority can be optimized independently72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/972227API
curl https://kongchang.com/api/v1/knowledge/claims/972227MCP
get_claim(id=972227)