Unverified50% confidenceBenchmarkExact time
On the GPQA Diamond scientific reasoning benchmark, the RSI inference engine ranks 1st among models under 500B parameters.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/13/2026
First Seen
Valid until: 10/27/2026
Sources
Related Entities
Related Claims
UnverifiedGPQA Diamond is a benchmark testing graduate-level scientific reasoning ability, with ordinary human performance at approximately 35% and top closed-source models in the 60–75% range.68% similarUnverifiedVIDRAFT achieved 93.43% in the sub-500B parameter category on GPQA Diamond.68% similarUnverifiedThe RSI inference engine achieved a perfect score of 100% on both the AIME 2026 math benchmark and the HMMT 2026 math benchmark, reportedly the first perfect score on a certified math leaderboard.64% similarUnverifiedGPTQ (2022) achieved the first usable performance of large models at INT4 by quantizing layer by layer and minimizing quantization error using Hessian information.63% similarUnverifiedThe evaluation covered five benchmarks: MMLU-Pro, GPQA Diamond, GSM8K, German MGSM, and IFEval.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1017280API
curl https://kongchang.com/api/v1/knowledge/claims/1017280MCP
get_claim(id=1017280)