Unverified50% confidenceFactExact time
A study on the Spanish MIR residency exam used four open-source models with 800 million to 27 billion parameters, grading 1,552 questions across eight sittings according to the exam's own rules.
1
Sources
50%
Confidence
Long-term
Relevance
10/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe test samples cover news reports and scientific abstracts, and the models invoked range from 3.8 billion to 753 billion parameters.72% similarUnverifiedArtificial Analysis consumed 160 million output tokens running the Qwen3.8-27B index, while the median for comparable open-weight models is 43 million, indicating that this model is verbose in its default reasoning.67% similarUnverifiedThe experiment was conducted on 400 samples drawn from three multi-hop QA datasets: MuSiQue, HotpotQA, and 2WikiMultiHopQA.67% similarUnverifiedMixtral 8x7B has a total of approximately 46.7 billion parameters, but only 2 experts are activated per inference, making the actual computation equivalent to a model of approximately 13 billion parameters.67% similarUnverifiedA study evaluated six knowledge tracing models on four public educational datasets and tested 12 threshold levels ranging from 0.50 to 0.99.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088172API
curl https://kongchang.com/api/v1/knowledge/claims/1088172MCP
get_claim(id=1088172)