Unverified50% confidenceBenchmarkExact time
OpenAI 6.2 Astra scored 78.3 on the Agent's Last Exam benchmark, 5.5 percentage points higher than Claude Fable 5.2.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/18/2026
First Seen
Valid until: 12/2/2026
Sources
OpenAI 6.2 Astra Hands-On Review Gone Wrong: Impressive Benchmarks, But Developers Say It's Unusable
youtubeTheo - t3․gg11/18/2026
Related Entities
Related Claims
UnverifiedOn the Bench 2.0 benchmark, an internal model scored 0.875 while Astra scored 0.594; the internal model's lowest reasoning tier scored 0.758, already surpassing Astra's result when running at full effort.73% similarUnverifiedAnthropic's released Fable 5.2 improved its score on the agentic science research benchmark from 52.6 for Fable 5.1 to 74.6, surpassing the score of Opus 5.5 and Astra's 68.1.72% similarUnverifiedOn Artificial Analysis's Intelligence Index, GPT-6.2 Astra scored 62, a 5-point improvement over the previous-generation Astra's 57, placing second, behind only Cloud Fable 5.2's 65.71% similarUnverifiedOpenAI 6.2 Astra scores 9 percentage points higher than the previous generation 6 Astra on Terminal Bench Science.69% similarUnverifiedFable 5.2 reaches a 41% automation rate on the Remote Labor Index (Remark benchmark), whereas a year earlier Opus 4.5 was only about 3.8%, and GPT-6 Astra reached about 21% in September.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1185489API
curl https://kongchang.com/api/v1/knowledge/claims/1185489MCP
get_claim(id=1185489)