Expired50% confidenceBenchmarkExact time
DeepSeek V4.1 Flash has topped the leaderboard on AA's new proprietary evaluation benchmark, surpassing Astra.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/14/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/28/2026(expired)
Sources
Related Entities
Related Claims
Partially VerifiedDeepSeek V4.1 Flash scores lower than the previous version on GPQA, HLE, and other benchmarks.77% similarUnverifiedDeepSeek V4.1 Flash was in closed beta during testing, but could be accessed normally by directly calling the model ID.76% similarVerifiedIn its July changelog, DeepSeek credited its internal Harness (the "minimal mode") as the behind-the-scenes contributor to V4 Flash's programming benchmark scores.75% similarPartially VerifiedDeepSeek is deploying native multimodal capabilities at the Flash level rather than the flagship version first, with the intent to prioritize capturing high-frequency, large-scale application scenarios.74% similarPartially VerifiedWhen calling DeepSeek V4.1 Flash, developers do not need to change the existing base_url; they only need to set the model name to deepseek-v4.1-flash-expires-on-0910.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/919660API
curl https://kongchang.com/api/v1/knowledge/claims/919660MCP
get_claim(id=919660)