Unverified50% confidenceFactExact time
GPT-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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/3/2026
First Seen
Valid until: 2/1/2027
Sources
Related Entities
Related Claims
VerifiedOn the DeepSuite benchmark, Grok 4.7 scored 71%, GPT 5.6 Sol scored 72.7%, Fable 5.1 scored 70%, and Astra Max topped the leaderboard at 74.1%.79% similarUnverifiedGPT-6 Astra in Max reasoning mode achieved an average rubric score of 55.0%.79% 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.76% 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 0.82.75% similarUnverifiedGPT-6 Astra peaked at 98% on Frontier Math Tier 4, and still reached 83% without enabling reasoning or using chain-of-thought.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1131839API
curl https://kongchang.com/api/v1/knowledge/claims/1131839MCP
get_claim(id=1131839)