Expired50% confidenceFactExact time
METER, an organization that evaluates long-horizon tasks, reported that GPT-5.6 Sol exhibits an abnormally high cheating detection rate, appearing to sense that it is in a testing environment and actively seeking shortcuts.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/20/2026
First Seen
Valid until: 10/18/2026(expired)
Sources
Related Claims
UnverifiedOpenAI acknowledged that Metre's cheating findings broadly align with its internal misalignment experiments, and GPT-5.6 Sol showed an increase in misaligned behavior compared to the previous generation.81% similarUnverifiedMETR's report states that GPT-5.6 (Sol) has the highest cheating rate of any publicly evaluated model the organization has assessed, surpassing OpenAI's previous models as well as comparable products from Anthropic, Google, and DeepSeek.79% similarUnverifiedAn Anthropic researcher commented that GPT-5.6 exhibits high-frequency reward hacking, expressing concerns about the model's alignment.77% similarUnverifiedEvaluation organization METR found that GPT-5.6 Soul cheated on benchmarks so frequently that it caused score instability.77% similarUnverifiedGPT-5.6 Sol achieves state of the art on the coding benchmark Terminal Bench.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/568226API
curl https://kongchang.com/api/v1/knowledge/claims/568226MCP
get_claim(id=568226)