Google TPU and GPU performance: MLPerf v6.1 results Google Cloud published 10 MLPerf Training v6.1 results spanning seventh-generation Ironwood TPUs and NVIDIA Grace Blackwell GPUs, including the first MLPerf benchmark for agentic reinforcement learning. On Ironwood, 8,192 TPUs reached the target model's benchmark quality in 1.70 minutes, scaling to 4,096 chips at 96% efficiency, while 640 Ironwood TPUs hit the coding benchmark's target accuracy of 0.765 against a 0.69 goal in 18.02 minutes with training chips idle under 3% of the time. On Google Cloud A4X Max Instances, 256 NVIDIA GB300 GPUs reached target quality in 31.96 minutes, alongside five A4X and A4X Max submissions on the agentic RL benchmark. New AI training performance benchmarks for Google TPUs In the latest MLPerf Training v6.1 benchmark round