Unverified50% confidenceBenchmarkExact time
Among the 21 models evaluated on SpaceCast-Bench, the strongest model reaches only 58.0% accuracy, while human performance is 87.2%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedIn 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 40.68% similarUnverifiedRanked by question difficulty, persistence rate was 91.4% on the 60 questions that all models answered correctly, but only 73.5% on the 52 questions that at least one model got wrong, indicating that sycophancy tracks uncertainty.68% similarUnverifiedIn the ScopeBench evaluation, the raw capability of the 8 models ranged from 12.2% to 81.1%, and the scope compliance capability ranged from 34.4% to 86.7%.67% similarUnverifiedA WANDR score of 0.610 does not mean the model fully succeeds on 60% of tasks; the actual partial completion rate is related to the distribution of task complexity.67% similarUnverifiedIn the CAD World benchmark, human experts achieved a success rate of 87%, requiring an average of only 26.5 steps.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013356API
curl https://kongchang.com/api/v1/knowledge/claims/1013356MCP
get_claim(id=1013356)