CoreWeave leads MiniMax M3 serving benchmark with 357 tokens/sec and $0.22/M
wandb · x · 2026-07-24
CoreWeave tops a speed benchmark for providers serving MiniMax M3
An Artificial Analysis chart shared by Weights & Biases compares providers serving MiniMax M3 on output speed, time to first token, and blended price.
- CoreWeave leads the board at 357 output tokens/sec.
- That is 1.8× faster than the next provider in the benchmark.
- It also shows the fastest time to first answer token at 6.6 seconds.
- The blended price is shown at $0.22 per million tokens, matching the lowest price on the chart.
- The comparison positions provider performance as a mix of latency, throughput, and price, not just raw speed.
More from Infra
- Intel Shares Surge 11% as AI Demand Drives Stronger-Than-Expected Earnings — econoar · 2026-07-24
- A 3 GW data-center load drop briefly stressed the PJM grid in Northern Virginia — Annual_Judge_7272 · 2026-07-24
- AMD Helios looks strong, but the Vera Rubin comparison is not apples to apples — karlfreund · 2026-07-24
- Artificial Analysis puts model intelligence and cost on San Francisco billboards — ArtificialAnlys · 2026-07-24
- NVIDIA’s Vera Rubin NVL72 cluster lands with 72 GPUs in one rack-scale system — rohanpaul_ai · 2026-07-24
- Intel’s Q2 2026 results land on the radar for AI infrastructure watchers — BenBajarin · 2026-07-24