Unverified50% confidenceBenchmarkExact time
On TriviaQA, the error rate of answered questions (under the exact match scoring criterion) decreased from 23.0% to 14.5%.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified业界仿真精度评估通常要求吞吐量误差小于15%73% similarUnverifiedAfter removing the candidate filtering component, FEVER accuracy dropped to 76.24%.71% similarUnverifiedPlacing verbose padding on the correct answer causes the judge's score to plummet—Grok non-reasoning hard-question scores dropped from 0.875 to 0.19—indicating that verbosity bias exists only in reverse.71% similarUnverifiedIn the control group where the answer key was removed from the prompt, the match rate plummeted from 63% to 1% (1/75).70% similarUnverifiedWhen users presented a wrong answer as a confident statement and pushed twice, the model persistence rate dropped from 94.4% to 84.0%.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002059API
curl https://kongchang.com/api/v1/knowledge/claims/1002059MCP
get_claim(id=1002059)