Unverified50% confidenceBenchmarkExact time
In 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/21/2026
First Seen
Valid until: 12/20/2026
Sources
Related Entities
Related Claims
UnverifiedGPT-6 Astra achieved a near-perfect score of 99.9% on ARC-AGI-type tests, while the average score of ordinary human test-takers was only 48%.74% similarUnverifiedEven GPT-4-level Agents often achieve end-to-end success rates below 60% on complex tasks involving more than 5 tool calls.71% similarUnverifiedIn max mode, GPT-5.6's score is actually slightly lower than in ultra mode, confirming the overthinking phenomenon.69% similarUnverifiedGPT-4 as a judge can achieve over 80% agreement with human evaluations, but exhibits systematic issues such as position bias, verbosity bias, and self-preference.68% similarUnverifiedIn the Artificial Analysis Intelligence Index comprehensive benchmark, GPT-5.6's performance is approximately 0.9 points lower than Claude Opus 4.5, but at nearly half the cost.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/938912API
curl https://kongchang.com/api/v1/knowledge/claims/938912MCP
get_claim(id=938912)