Unverified50% confidenceBenchmarkExact time
When the 35B model switched to a wider context, its pass rate plummeted to 46/90, with 43 responses truncated due to a fixed output budget.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe 35B model achieved a pass rate of 90/90 under the constrained context, while the 4B model achieved 72/90.70% similarUnverified21.2% is a relative reduction rather than an absolute one, meaning the new version eliminates approximately one-fifth of the failures relative to the earlier version's failure rate baseline.68% similarUnverifiedWhen models were provided with complete company records, strict accuracy actually dropped from 41% to 18%, while recall rose and precision collapsed.67% similarUnverified将FP32权重降至INT8后，典型Transformer模型基准测试分数下降通常不超过1%，推理速度提升2至4倍，内存占用减少75%67% similarVerifiedFor models with more than 30B parameters, the performance loss caused by 4-bit quantization typically results in a 1–3% drop on benchmarks, but the impact is more significant for smaller models.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1000039API
curl https://kongchang.com/api/v1/knowledge/claims/1000039MCP
get_claim(id=1000039)