Unverified50% confidenceBenchmarkExact time
The model's score of 535.4 far exceeds the IOI gold medal threshold of 361.12 and surpasses the top human contestant's score of 498.27 in that competition.
1
Sources
50%
Confidence
Long-term
Relevance
9/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn Path A, an RTX 3060 runs the front layers and an AMD AI Max+ 395 runs the back layers, improving Prefill speed from 136.69 token/s to 319.1 token/s under IQ3 quantization with 64K long input.61% similarUnverifiedComparison data from the paper: the best individual foundation model alone has an average MASE rank of 33.8, per-configuration tournament selection is 38.0, and the full router is 19.4.60% similarUnverifiedAccording to Artificial Analysis leaderboard data, DeepSeek V4 Pro's score increased from 52 to 53, a difference of only 1 point.59% similarUnverified在覆盖九大维度共403道题的测试中，Muse-Glimmer-30B综合均分为76.04，比Corpus 3.6 27B的75.57高出0.47分58% similarUnverifiedDeepSeek V4 Pro scored 37.7 on the Humanity's Last Exam benchmark.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/958398API
curl https://kongchang.com/api/v1/knowledge/claims/958398MCP
get_claim(id=958398)