Expired60% confidenceBenchmarkExact time
Qwen2.5-72B approaches the performance of Llama-3.1-405B across multiple benchmarks.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/20/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/18/2026(expired)
Sources
Related Claims
UnverifiedThe test was conducted based on the Qwen3 27B NVFP4 quantized version released by Unsloth.79% similarUnverifiedQwen2.5-7B-Instruct's performance on multiple Chinese benchmark tests is close to or even surpasses that of early 70B-level models.77% similarUnverifiedThe original Qwen3.5-0.8B has NLL of 2.905585 and PPL of 18.2759; Qwengram-0.8B has NLL of 2.853786 and PPL of 17.3534.77% similarUnverifiedQwen3.5-122B-A10B produced 8 refusals in 100 tests, with a KL divergence of 0.0856.76% similarUnverifiedThe author noted that other models previously tested, such as 35B and 3B variants, actually performed worse than the Q2 version of Qwen3 27B on the Kanban task.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/566754API
curl https://kongchang.com/api/v1/knowledge/claims/566754MCP
get_claim(id=566754)