Unverified50% confidenceBenchmarkExact time
Qwen3-1.7B's overall causal faithfulness is only 54.8%, far below that of Qwen3-4B.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedQwen3-1.7B's faithfulness is 68% on 2-hop tasks but plummets to 30% on 6-hop tasks, whereas Qwen3-4B remains relatively stable across different hop counts.78% similarUnverifiedThe random-position null baseline for Qwen3-4B was only 11.3%, and the upper bound for directly patching lower-level prompt facts was 83%.78% similarVerifiedQwen3.5's parameter activation rate is 4.3%, while DeepSeek V3's 671B model has an activation rate of 5.5%.77% similarUnverifiedQwen 3.6 Max has an end-to-end accuracy of only 12.3% in neutral mode77% similarUnverifiedQwen3-4B is already on par with DeepSeek V3 or GPT-4o on multiple reasoning evaluation metrics.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946176API
curl https://kongchang.com/api/v1/knowledge/claims/946176MCP
get_claim(id=946176)