Expired50% confidenceBenchmarkExact time
In 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/13/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/11/2026(expired)
Sources
GPT-5.6发布：三款模型对标Claude，ChatGPT Work超级应用全解析
bilibiliAI-seeker7/9/2026
Related Claims
UnverifiedGPT 5.2 scored approximately 77% on competition problems in frontier science benchmarks, but its performance dropped to approximately 25% on open-ended research tasks.73% similarUnverifiedIn max mode, GPT-5.6's score is actually slightly lower than in ultra mode, confirming the overthinking phenomenon.72% similarUnverifiedRunning benchmark tests with Opus 5 at Medium settings combined with Ponytail resulted in noticeably fewer output tokens, with costs actually approximately 22% lower.72% similarUnverifiedThrough a series of strategy adjustments, the usage cost of Opus 5 can be reduced by up to 80%, while still outperforming Opus 4.8 on some benchmarks.72% similarUnverifiedClaude Opus 4.8's most significant advancement is a dramatically lower error rate during actual use rather than improved benchmark scores71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501554API
curl https://kongchang.com/api/v1/knowledge/claims/501554MCP
get_claim(id=501554)