Unverified50% confidenceBenchmarkExact time
On these 14 tasks, the GPT-6 Astra coding agent achieved an average Q value of 0.639, compared with only 0.108 for the learned policy.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/11/2026
First Seen
Valid until: 11/25/2026
Sources
Related Entities
Related Claims
UnverifiedGPT-6 Astra raised the MATH-500 score from 7.9% to 48.1% under the same sampling settings by natively editing 0.016% of the weights of Qwen3.5-0.8B.76% 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.73% similarUnverifiedOn Autonomous Science Bench, SciMARS + Memory solved 12 of 18 GPT-6-Astra attempts, while the base multi-agent team solved only 8/18.72% similarUnverifiedGPT-6 Astra in Max reasoning mode achieved an average rubric score of 55.0%.71% similarUnverifiedGPT-6 Astra achieved the best performance among the eight models with an average score of 0.90, followed by Claude Opus 5 with an average score of 0.82.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1158635API
curl https://kongchang.com/api/v1/knowledge/claims/1158635MCP
get_claim(id=1158635)