Unverified50% confidenceFactExact time
Version 1.2.3 includes test fixes for Scaleway streaming models (#41095).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/10/2026
First Seen
Valid until: 1/8/2027
Sources
Related Entities
Related Claims
UnverifiedThe fine-tuned 406M model achieved 36.33 ROUGE-1 on the test set, while the authors' own 1.2B system achieved 35.41 ROUGE-1, and the two cannot be statistically distinguished.61% similarUnverifiedThe test used the minimax_h3_fl2va_int8_convrot model.60% similarUnverifiedThe test was conducted based on the Qwen3 27B NVFP4 quantized version released by Unsloth.59% similarUnverifiedReLE's commercial model evaluation covers domestic models including Wenxin ERNIE-X1.1, ERNIE-5.0, qwen3.6-max, Baichuan, iFlytek Spark, and SenseTime senseChat.58% similarUnverifiedMeta's Llama 3.1 supports 405B parameters, and open-source models including Qwen2.5 and DeepSeek-V3 have approached or even surpassed some closed-source commercial models on multiple benchmarks.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/993342API
curl https://kongchang.com/api/v1/knowledge/claims/993342MCP
get_claim(id=993342)