Expired50% confidenceEventExact time
The developer used a free trial week of a Step 5 model on OpenRouter to test large-scale context dumping, and the model was able to correctly parse a context window of 1 million tokens while maintaining tool-calling integrity.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/8/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/22/2026(expired)
Sources
Related Entities
Related Claims
Unverified使用OpenTrade建议从模拟盘、极小额度开始，验证Agent行为稳定性和护栏可靠性后再扩大规模70% similarUnverifiedThe research team conducted extensive evaluations using multiple agent frameworks on both proprietary models and open-weight models; state-of-the-art models such as GLM-5.2 and Claude-Sonnet-4.6 achieved only slightly above passing performance.68% similarUnverifiedThis update supports training directly on pre-quantized 4-bit checkpoints at their published weights, so that the memory required by the loaded model is roughly equivalent to the 4-bit checkpoint itself67% similarUnverifiedThe model's intelligence is essentially unimpaired on five real Coding Agent problems, with both the Preview and 0731 versions passing all tests.67% similarUnverified大模型第一阶段的评测涌现了OpenCompass、Evascope等工具及GSM8K等标准数据集66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/988420API
curl https://kongchang.com/api/v1/knowledge/claims/988420MCP
get_claim(id=988420)