Unverified50% confidenceBenchmarkExact time
In the BioPhys-Bridge evaluation, DeepSeek-V4-Flash achieved the highest score with an evidence ID F1 score of 0.360.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/18/2026
First Seen
Valid until: 12/17/2026
Sources
Related Entities
Related Claims
UnverifiedIn the BioPhys-Bridge evaluation, Qwen3.7-Max's evidence ID F1 score is 0.316.78% similarUnverifiedV4.1-Flash scored 74.2 points on a certain programming test dimension, an improvement of nearly 20 points over V4-Flash.68% similarUnverifiedDeepSeek V4 Pro scored 37.7 on the Humanity's Last Exam benchmark.65% similarUnverifiedMiniCPM5-2B achieved a composite score of 15 on the Artificial Analysis Intelligence Index v4.2 benchmark, ranking first among open-source models with fewer than 4B parameters.64% similarUnverifiedOn 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.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/931049API
curl https://kongchang.com/api/v1/knowledge/claims/931049MCP
get_claim(id=931049)