Unverified50% confidenceBenchmarkExact time
On the DeepSWE v1.1 benchmark, 3.8 Flash surpasses most frontier models with larger parameter counts.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/12/2026
First Seen
Valid until: 12/11/2026
Sources
Related Entities
Related Claims
UnverifiedV4.1 Flash surpassed Opus 5 on the DeepSWE benchmark by a narrow margin of 0.2 points.80% similarUnverifiedIn that test, DeepSeek V4 Flash official release was approximately 3.6 times faster than the Pro preview version.79% similarUnverifiedDeepSeek V4.1 Flash claims to achieve breakthroughs across three dimensions: capability, speed, and cost.78% similarUnverified盘古2.0 Flash在GPQA Diamond科学推理测试中（Thinking模式）得分83.7，低于千问3.6 35B的86、27B稠密模型的87.8和DeepSeek V4 Flash的88.174% similarUnverifiedDeepSeek V4.1 Flash is on par with GLM 5.3 and Kimi K3 on several key benchmark tests.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/912483API
curl https://kongchang.com/api/v1/knowledge/claims/912483MCP
get_claim(id=912483)