Unverified50% confidenceBenchmarkExact time
gpt-oss-20b's weakness is source attribution—out of 60 questions, it fully listed all sources only 52 times.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
Unverified46个模型中有41个完整跑完全部28道题，3个因服务错误未完成，GPT-5.6 Terra因配额限制止步24/28，GPT-6 Astra只跑了1道题65% similarUnverifiedThe 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 0.38.65% similarUnverifiedGPT-5.5 ran out of usage quota, leaving 35 of the 90 questions unfinished; all 55 answered questions were correct, but Kaggle counted the unanswered questions as wrong, causing its official score to be lower.63% similarUnverifiedIn the Artificial Analysis overall intelligence index, GPT-6 Sol scores a full 48 points (in the same tier as Astra), and Luna scores a full 36 points.61% similarUnverifiedClaude Haiku 4.5 answered 'not found' in 21 of its 24 errors on two-step questions, while GPT-5.4 mini copied the literal wording of the referral as the answer in 20 of its 27 errors, and fabricated real-sounding names while citing actual documents in another 7.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003224API
curl https://kongchang.com/api/v1/knowledge/claims/1003224MCP
get_claim(id=1003224)