Unverified50% confidenceBenchmarkExact time
In Deep Principle's own FrontierScience Research (FSR) benchmark, Hydrogen-1.0 achieved a pass rate of 38.3%, surpassing GPT-6 Astra's 33.3%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/4/2026
First Seen
Valid until: 2/2/2027
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%.67% similarUnverifiedGPT-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.65% similarUnverifiedIn the GDP PDF evaluation, GPT-6.1 Sol scored 32.0%, Astra scored 32.2%, and Opus 5.5 with a fallback mechanism scored 28.8%.65% similarUnverifiedIn the correspondence rate with papers published after the model's cutoff date, DiscoveryRSI-27B reached 6.3%, GPT-6 was 2.5%, and Claude Opus 5 was 2.3%.64% similarUnverifiedOn the HLE benchmark, COMED improved GPT-5.5's performance from 23.1% to 28.1%.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134456API
curl https://kongchang.com/api/v1/knowledge/claims/1134456MCP
get_claim(id=1134456)