OpenAI's Jalapeño chip reportedly beats Nvidia GB200 in benchmarks
mark_k · x · 2026-08-26
Reports from Hot Chips suggest that OpenAI's first inference chip, Jalapeño, performs better than expected. Benchmarks against models like GPT-OSS 120B, DeepSeek R1 670B, and Kimi K2.5 1T show it delivers 1.5-1.9x better performance per watt and 1.7-3.6x lower end-to-end latency than Nvidia's GB200/GB300 Blackwell systems. Notably, OpenAI used its own AI (Codex + GPT-Astra) to design the chip, with AI-generated kernels outperforming expert-written ones by 1.5-1.8x in specific blocks.
More from Infra
- engy.ai processes 50B+ tokens in a day as open-model inference demand surges — const_reborn · 2026-10-16
- New inference engine 'e' hits 10,500 tok/s on a single DGX Station — brandon_galang · 2026-10-16
- SGLang ships Day-0 support for FLUX 3 Image Klein: 10 reference images, BF16/FP8/NVFP4 variants — ying11231 · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Chip equipment beats bull case: 2026 WFE seen at $153B, $278B by 2030 — BenBajarin · 2026-10-16
- Steam now launches in 5.23s, beating Epic's 5.47s — and vLLM gets roasted for slow startup — AlpinDale · 2026-10-16