Unverified50% confidenceBenchmarkExact time
Under the DeepSuite V1.1 benchmark, the same model's scores fluctuate from 69.8% to 74.2% across different harnesses.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/18/2026
First Seen
Valid until: 12/17/2026
Sources
Related Entities
Related Claims
UnverifiedAt this compression ratio, the model retains 74.2% top-1% accuracy74% similarUnverifiedAt the mention level, the model achieved an overall precision of 74.1% and a recall of 70.5%.67% similarUnverifiedRunning Terminal Bench on the same model under different harnesses produced scores ranging from 69.8% to 74.2%.66% similarUnverifiedFor the 7B model, accuracy with the solver was 75.31% versus 72.02% for direct calculation, a paired improvement of +3.29 percentage points, with a 95% cluster interval of [-3.49, 10.38] crossing zero, making the advantage non-significant.66% similarUnverifiedAs the model scales from 8B to 70B, the predictive power of fixed output vector similarity for behavior actually worsens, with a paired mean correlation change of -0.080 (95% confidence interval [-0.127, -0.035]).65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/932819API
curl https://kongchang.com/api/v1/knowledge/claims/932819MCP
get_claim(id=932819)