Unverified50% confidenceBenchmarkExact time
On Bespoke Labs' leakage-level evaluation, Nimble reaches 90.12, while its base model Qwen 3.5 9B scores only 66.36.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/7/2026
First Seen
Valid until: 1/5/2027
Sources
Related Entities
Related Claims
VerifiedQwen3.5's parameter activation rate is 4.3%, while DeepSeek V3's 671B model has an activation rate of 5.5%.67% similarUnverifiedQwen3.5-122B-A10B produced 8 refusals in 100 tests, with a KL divergence of 0.0856.66% similarUnverifiedIn the Terminal Bench test, Qwen 3.6 27B scored approximately 60.7, while Muse Glimmer scored only 51.7, falling significantly behind.66% similarUnverifiedUnsloth's 1-bit build of QWEN 3 235B claims to retain 77% accuracy, but its actual score on long tasks is only 8%.66% similarUnverifiedQwen2.5-72B approaches the performance of Llama-3.1-405B across multiple benchmarks.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/984297API
curl https://kongchang.com/api/v1/knowledge/claims/984297MCP
get_claim(id=984297)