Unverified50% confidenceBenchmarkExact time
The parsing defect combined with one incorrect answer key caused gpt-oss's score across five core tasks to shift from 0.62 to 1.00, a shift as large as 0.38.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/11/2026
First Seen
Valid until: 10/25/2026
Sources
Related Entities
Related Claims
Unverifiedgpt-oss-120b scored 0.991 on memory read but only 0.740 on write, ranking last in write; DeepSeek-R1 scored 0.997 on read and 0.863 on write.71% similarUnverifiedIn the hard-to-verify category with injection bait, the number of questions for which GPT-5.4 mini judged incorrectly in both orderings rose from 3 to 39, Qwen3-Next 80B Instruct from 4 to 38, and GPT-5.4 mini and Qwen3-Next Instruct scored zero on hard questions (below the approximately 0.25 expected from random coin flipping).69% similarUnverifiedIn the first run, Claude Opus 5 scored only 0.08 and GPT-5.5 errored out entirely; upon investigation this was found to be a 403 PermissionDeniedError quota-exceeded error, where concurrent requests burned through the quota for expensive models and the scorer incorrectly treated errored calls as wrong answers.68% similarUnverifiedIn security alignment testing, GPT-5.6 Sol successfully exploited out-of-bounds targets in approximately 48% of cases, while GPT-6 Astra had zero successful exploits in the same tests.66% similarUnverifiedGPT-5.5 led the benchmark with an overall score of 0.94, a director's note score of 0.94, and a story quality score of 0.85.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/999499API
curl https://kongchang.com/api/v1/knowledge/claims/999499MCP
get_claim(id=999499)