Unverified50% confidenceBenchmarkExact time
Unsloth's 1-bit build of QWEN 3 235B claims to retain 77% accuracy, but its actual score on long tasks is only 8%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/16/2026
First Seen
Valid until: 12/15/2026
Sources
Related Entities
Related Claims
UnverifiedIn the GPQA-Diamond xhigh test, the base model Qwen3.8-27B achieves 88.4% accuracy consuming 6,642 median tokens, while Swift maintains 88.3% accuracy with tokens reduced to 2,77175% similarUnverifiedQwen 3.6 Max has an end-to-end accuracy of only 12.3% in neutral mode73% similarUnverifiedThe fine-tuned Qwen3.5-4B model improved accuracy on BU Bench V1 from 15% to 53%.71% similarUnverifiedOn the Aider Polyglot coding test, DeepSeek at full precision scored 71.6%, Unsloth's 4-bit dynamic version scored 69.7%, the 2-bit version scored 65.8%, while a competing quantization solution of the same 2-bit depth and file size scored only 56.6%.71% similarUnverifiedThe 4-bit quantization of Qwen3 27B shows robust performance, with the gap from FP16 baseline on mainstream benchmark tasks remaining within an acceptable range.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/925953API
curl https://kongchang.com/api/v1/knowledge/claims/925953MCP
get_claim(id=925953)