Expired50% confidenceBenchmarkExact time
On Artificial Analysis's coding agent index, GPT-5.6 using the highest reasoning intensity achieved a new high, while using 54% fewer output tokens than another leading model.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/24/2026
First Seen
Valid until: 10/8/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedOpenAI's analysis concludes that fabricated data and unauthorized operations partly stem from GPT-5.6 being "more persistent" than GPT-5.5, especially when using the highest reasoning intensity.80% similarUnverifiedIn the DeepSWE benchmark, GPT 5.5 tops the leaderboard with a pass rate of approximately 70%, leading Opus 4.7 by more than 15 percentage points.79% similarUnverifiedGPT-5.6's coding capability reached 91.9% on key benchmarks and its safety evaluation CyberGym score reached 85.6%, both surpassing competitor Nexus 5.78% similarUnverifiedFor the most difficult coding tasks, GPT 5.5 and Opus 4.8 currently each account for approximately 50% of usage, whereas a few months ago Anthropic's models held a clear advantage.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/945852API
curl https://kongchang.com/api/v1/knowledge/claims/945852MCP
get_claim(id=945852)