Unverified50% confidenceBenchmarkExact time
In the Sighted (visible board) trials, models made a first move consistent with the reference answer in 26.1% of cases, but ultimately won the game in only 13.9% of cases.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedUnder the influence of multi-turn narratives, the models' final judgments shifted by an average of 25 percentage points compared to matched single-turn baselines.69% similarUnverifiedSparse and dense rewards are statistically indistinguishable on in-domain success rate, but the gap reaches 33 percentage points on held-out calibration probe tests.69% similarUnverifiedIn an unknown-rules mini-game test designed specifically for models, GPT-6 scored 99 points, approaching a perfect score, while the highest human score was only in the 30s and other models scored around 40.67% similarUnverifiedOn a test subset of 152 completely untouched questions, anchored hybrid retrieval achieved 42.11%, while the planner-guided method reached only 36.84%.65% similarUnverifiedAfter introducing a gating mechanism based on the measurement metrics, accuracy improved from 20.7% to 36.9%, while the system still answered half of all comparisons.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975458API
curl https://kongchang.com/api/v1/knowledge/claims/975458MCP
get_claim(id=975458)