Unverified50% confidenceBenchmarkExact time
Luna never imported historical changes during the Forge test—none of the 62 historical changes were included—triggering a backfill check labeled as critical, which multiplied the entire round's score by 0.6, changing it from 0.6583 to 0.395.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/12/2026
First Seen
Valid until: 10/26/2026
Sources
Related Entities
Related Claims
UnverifiedThe Luna model's fail_fast/endstate score is 64/55, with the gap corresponding to trajectories that appear clean turn by turn but end in a corrupted final state.60% similarUnverifiedLuna配置在HIGH和XH模式下10次测试全部答错，正确率为零56% similarUnverifiedLuna's performance was evaluated as mediocre, with the model exhibiting many errors and falling short of GPT-6.1 and Sonnet 5.5 in stability and accuracy.56% similarUnverifiedLuna scored 66.6% in the coding test, with costs 93% and 96% lower than Opus 5 and Fable 5, respectively.56% similarUnverifiedOn a pure parity task, GAN8 achieved 100%, JEV MLP achieved 67%, and JEV linear achieved 33%.53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003253API
curl https://kongchang.com/api/v1/knowledge/claims/1003253MCP
get_claim(id=1003253)