Unverified50% confidenceBenchmarkExact time
In a comparative test on 29 real blunders, the bare Gemma model correctly named Stockfish's top alternative move 0 out of 29 times.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
Related Entities
Related Claims
UnverifiedIn a comparative test on 29 real blunders, the bare Gemma model mentioned illegal moves not on the board 7 out of 29 times.75% similarUnverifiedFiorillo v0.5's log loss is 0.8603 lower than the prior baseline and 0.1829 lower than the Gemma model reading the same input.63% similarUnverified仅用小模型策略的每正确答案成本最低($0.0004)但准确率仅33%，说明没有准确率底线的每正确答案成本指标具有误导性62% similarUnverifiedA sample size of 30 is relatively small, and this accuracy rate is better suited as a feasibility validation rather than a rigorous performance benchmark.60% similarUnverifiedPure tournament selection (38.0) performs worse than the best single model (33.8), indicating that per-configuration selection suffers from overfitting the backtest.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1053949API
curl https://kongchang.com/api/v1/knowledge/claims/1053949MCP
get_claim(id=1053949)