Expired60% confidenceBenchmarkExact time
In the GDP Val benchmark, Grok 4.6 high ranked first.
2
Sources
60%
Confidence
Short-term (~14 days)
Relevance
8/16/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Claims
UnverifiedOn the GDP Val benchmark (a benchmark introduced by OpenAI to measure effectiveness on real knowledge-work tasks), Grok 4.6 high achieved first place.77% similarUnverifiedGrok 4.6的智能指数比Grok 4.5高5分，比Grok 4.3高23分71% similarPartially VerifiedClaude Opus 4.8 scored 69.2% on the SWE-bench benchmark, compared to 58.6% for GPT 5.5 and 54.2% for Google Gemini.64% similarUnverifiedClaude Sonnet 4.6 scored higher than Opus 4.6 on the GDPVal AA benchmark.63% similarUnverifiedGPT-5.6 set a new all-time high score of 53.6 on the Agent's Last Exam benchmark, surpassing Claude Opus 4.5 by 13.1 points.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/756906API
curl https://kongchang.com/api/v1/knowledge/claims/756906MCP
get_claim(id=756906)