Tencent Hunyuan Hy4 tops CWE-Bench-AA and ranks third on Cyber Index
Artificial Analysis reports that Tencent Hunyuan Hy4 scored 58% on its Cyber Index, ranking third behind Kimi K3.1 Pro and GPT-6 Sol (Daybreak Blue, max). Hy4 placed first on CWE-Bench-AA with 76%, leading DeepSeek V4.1 Flash 1017 (max) by six points in an implementation of Collinear AI's CWE-bench v1. Artificial Analysis also reported API pricing of $0.834 per million input tokens and $2.501 per million output tokens, with a cost of $0.92 per task on its capability-cost frontier.
The independently measured results position Hy4 as a leading model for vulnerability-fixing agents while placing it on Artificial Analysis's capability-cost Pareto frontier.
Tencent's Hy4 ranks #3 on the Artificial Analysis Cyber Index and #1 on CWE-Bench-AA
@TencentHunyuan's Hy4 scores 58% on the Artificial Analysis Cyber Index, 1 point ahead of DeepSeek V4.1 Flash 1017 (max). It trails Kimi K3.1 Pro (64%) and the trusted-access GPT-6 Sol (Daybreak Blue, max) (69%). API pricing is $0.834/$2.501 per 1M input/output tokens.
Key results:
➤ #1 on CWE-Bench-AA (76%). Hy4 leads DeepSeek V4.1 Flash 1017 (max) by 6 points on our implementation of @CollinearAI's CWE-bench v1, which tests agents' ability to find and fix real software vulnerabilities
➤ Strong capability for the cost. At $0.92 per task, Hy4 sits on the Capability vs. Cost Pareto frontier. It scores 2 points above Grok 4.7 (xhigh) at 1/11th the cost and 1 point above DeepSeek V4.1 Flash 1017 (max) at 2x the cost
➤ Fewer output tokens than peers. Hy4 uses 64k output tokens per task: 43% fewer than DeepSeek V4.1 Flash 1017 (max) and 37% fewer than Grok 4.7 (xhigh), but 49% more than Kimi K3.1 Pro and 56% more than GPT-6 Sol (Daybreak Blue, max)

#Tencent Hunyuan Hy4#Tencent Hunyuan#Artificial Analysis Cyber Index#CWE-Bench-AA#CWE-bench v1#DeepSeek V4.1 Flash 1017#Kimi K3.1 Pro#GPT-6 Sol#Grok 4.7#Collinear AI