AMD MI355X 跑分出炉：Artificial Analysis 将其纳入 AA-AgentPerf 对比 NVIDIA
AMD MI355X 和 NVIDIA B200/B300 跑智能体工作负载的对比数据来了，DeepSeek V4 Pro 上每瓦吞吐反超 B200 最多 40%，但高负载下被拉开，想选卡部署的可以看数据。
Artificial Analysis 把 AMD 的 MI355X 加入了自家的 AA-AgentPerf 基准，该基准通过重放真实的智能体编程会话来测量推理性能，覆盖 DeepSeek V4 Pro、DeepSeek V4.1 Flash、GLM-5.2/5.3 和 Kimi K3 四个模型。MI355X 拥有 288GB HBM3E（B200 为 180GB）和约 10 PFLOPS 的 FP4 算力。在 DeepSeek V4 Pro 0813 上，MI355X 在每用户 35-75 tok/s 区间比 B200 每兆瓦多输出 15% 到 40% 的吞吐。但在高负载场景下差距明显：DeepSeek V4.1 Flash 在每用户 100 tok/s 时约为 128M tokens/s/MW，而 B200 达到约 193M，B300 达到约 220M。Kimi K3（2.8T 参数）上单智能体速度为 152 tok/s，低于 B300 的 235 tok/s。
In addition to our new DeepSeek V4.1 Flash results, we’re adding AMD’s MI355X to AA-AgentPerf for Kimi K3, GLM-5.2/5.3 and DeepSeek V4 Pro - comparing it to our latest results for NVIDIA systems on coding agent workloads.
AA-AgentPerf is our agentic inference performance benchmark. It replays real agentic coding sessions, including prompt caching and tool-call delays, to give a realistic measure of inference performance in day-to-day agentic workloads.
MI355X is AMD's flagship accelerator in the MI350 series, launched in June 2025 on its CDNA 4 architecture. It has the same 288GB of HBM3E at 8TB/s as NVIDIA's B300, around 10 PFLOPS of dense FP4 compute (vs. B300 at ~13.5 and B200 at ~9) and board power of up to 1,400W. All our MI355X results use ROCm nightly and dev builds of vLLM and SGLang.
We are debuting results for AMD's MI355X on a single 8-GPU node across all four featured AA-AgentPerf models. Results on our leaderboard are live and will evolve over time - we look forward to tracking software/serving improvements on AMD hardware.
Initial results on MI355X:
➤ Its strongest result is on DeepSeek V4 Pro 0813, where MI355X serves ~15% to 40% more throughput per MW than B200 between 35 and 75 tok/s per user, likely helped by its 288GB of HBM per GPU (B200 has 180GB) on a 1.6T parameter model
➤ On DeepSeek V4.1 Flash, MI355X is in line with NVIDIA Blackwell for a single agent at 647 tok/s (B300 at 652, B200 at 669), but falls behind as load rises, reaching ~128M tokens/s per MW at 100 tok/s per user against ~193M for B200 and ~220M for B300
➤ On GLM-5.2/5.3, MI355X trails B200 and B300 at 100 tok/s per user, with ~26M tokens/s per MW against ~42M and ~44M respectively
➤ On Kimi K3 (2.8T parameters), MI355X serves ~8M tokens/s per MW at 50 tok/s per user against ~24M for B300 using NVIDIA's multi-node configs, and 152 tok/s for a single agent against 235
