Unverified50% confidenceFactExact time
Reportedly, each successful mathematical result required on average only about 3 hours of ChatGPT Pro-equivalent compute for thinking.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/8/2026
First Seen
Valid until: 1/6/2027
Sources
Related Entities
Related Claims
UnverifiedIn 2023, the formal verification of the polynomial Freiman-Ruzsa conjecture led by Terence Tao took only three weeks.63% similarUnverifiedUnder a 15-minute time limit per problem, the proof agent achieved a successful proof rate of 34.9% (157/450) on StochBench.61% similarPartially VerifiedThe author consumed only about 3% of the monthly quota after extensive testing for an entire day, suggesting that GPT-6.1 Sol's token efficiency is quite good61% similarUnverifiedOn the most difficult 3D watch task, Qwen 3 Max scored only 3 points and did not fully implement all features, though the highest score on that task was 4 points by the Claude flagship.61% similarUnverifiedTernary quantization theoretically requires only approximately 1.58 bits (log₂3) per weight for representation.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/989112API
curl https://kongchang.com/api/v1/knowledge/claims/989112MCP
get_claim(id=989112)