Unverified50% confidenceBenchmarkExact time
On AdvBench against DeepSeek-V4-Flash, the best static baseline achieves only 54.8% ASR@1 with a fixed 7 turns.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/27/2026
First Seen
Valid until: 1/25/2027
Sources
Related Entities
Related Claims
UnverifiedOn AdvBench against DeepSeek-V4-Flash, SEMA-Auto achieves 76.0% ASR@1 within an average of 3.0 turns.72% similarUnverifiedFlash 1017 scores 68.9% on LongBench QA top-5, higher than DeepSeek V4-Pro's 66.1% and GPT-4-Turbo's 62.3%.66% similarUnverifiedDeepSeek's model V4 Flash 0731 achieved a score of 82.7% on Terminal-Bench 2.1.61% similarVerifiedV4.1 Flash surpassed Opus 5 on the DeepSWE benchmark by a narrow margin of 0.2 points.60% similarUnverifiedOn the automation bench, DeepSeek V4.1 Flash version 1017 scored 60 points, while Opus 5 scored 50.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1103175API
curl https://kongchang.com/api/v1/knowledge/claims/1103175MCP
get_claim(id=1103175)