Chip Comparisons

286 head-to-head inference benchmark comparisons across DeepSeek V4 Pro 1.6T, DeepSeek R1, Kimi K3 2.8T, Kimi K2.5/K2.6/K2.7-Code 1T, GLM 5/5.1, GLM 5.2, MiniMax M3 428B, MiniMax M2.5/M2.7, Qwen 3.5 397B-A17B, gpt-oss 120B, and Llama 3.3 70B. Each page includes interactive charts for latency, throughput, and cost metrics, plus an interpolated comparison table.