Unverified50% confidenceBenchmarkExact time
DeepSeek V4.1 Flash scored 42 on Humanities Last Exam, tied with Kimi K3 and GLM 5.3; its Terminal Bench score was also 42.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/28/2026
First Seen
Valid until: 11/11/2026
Sources
Related Entities
Related Claims
UnverifiedOn a three-sample math problem, DeepSeek V4.1 Flash scored 74 points, on par with Opus 5.0 and surpassing GLM's 67 points and V4 Pro's 62 points.73% similarUnverifiedVendor-reported data shows that Kimi K3 scores 93.5 on GPQA Diamond and 76.8 on SWE-bench Verified; DeepSeek V4.1 Flash reports a score of 90.6 on Terminal-Bench 2.1.71% similarUnverifiedMiMo-V2.6-Pro (1T parameters) scores 46, while DeepSeek V4.1 Flash 1017 (552B) and GLM-5.3 (753B) both score 45.68% similarUnverifiedThe model card gives GLM-5.3-Flash's benchmark scores: 84.3 on Terminal-Bench 2.1 and 63.4 on DeepSWE.68% similarUnverifiedDeepSeek-V4.1-Flash-1017's score on Terminal-Bench 4.0 rose from 31.2 for V4.1-Flash to 42.3.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1109674API
curl https://kongchang.com/api/v1/knowledge/claims/1109674MCP
get_claim(id=1109674)