Unverified50% confidenceEventExact time
Mikhail Maslenik reproduced Tīrtha Bench's 800 requests on his own machine using a quantized copy of the same model, and scoring with Berkeley's official checker yielded 90.6%, while Tīrtha's own result was 91.0%, a difference of three out of the 800 tasks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedThe same open model, gpt-oss-120b, scored anywhere from 63.9% to 78.0% on the same 800 tasks depending on the four different hosting providers.65% similarUnverifiedEmpirical data shows that the cumulative input cache hit rate was approximately 92.5% for coding tasks and approximately 97.8% for web tasks.62% similarUnverifiedAmong the 12 model × task combinations, only gpt-5.4-mini showed a statistically significant accuracy improvement on the logical reasoning task: jumping from 15% to 97.5%, with p=0.00056 after Holm correction.60% similarUnverifiedOn the MNIST CNN task, MaRN compressed trainable parameters from 107,998 to 1,872 (approximately 57.7x), while maintaining 91.80% accuracy.60% similarUnverifiedCalibration refers to a judge who is 70% confident in 100 events having approximately 70 of those events actually occur, in which case the judge is said to be well-calibrated.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1064723API
curl https://kongchang.com/api/v1/knowledge/claims/1064723MCP
get_claim(id=1064723)