Benchmarking inference at scale: coding agents

The article presents a benchmark comparing Together Inference Engine against TensorRT-LLM and SGLang on a coding agent workload using Kimi K2.5. It reports that Together Inference Engine achieves 31% higher tokens per second (TPS) and 2× better time-to-first-token (TTFT) at saturation, attributed to full-stack optimizations including ThunderMLA and custom kernel rewrites.

From the source
On a production coding agent workload, Together Inference Engine delivers 31% more TPS than the next fastest OSS engine on the same hardware, and maintains 2× better TTFT at saturation.
together.ai

Visit source ↗together.ai

Announced: 19 May 2026 00:00 UTC
Detected: 03 Aug 2026 21:12 UTC (+76d after)

Other stories

Together AI · 28 AugGLM-5.3 vs. GLM-5.3 Flash on DeepSWE: Cost, Coding, and Routing

Google Research · 27 AugPlanetary prediction engine: Automating global models via Earth AIResearch paper

OpenAI · 27 AugBetter answers, broader thinking: What students gain from ChatGPT and critical-thinking trainingResearch paper

LG AI Research · 27 Aug

[ACL 2026] ReSQL: A Self-Improving Text-to-SQL Framework through Retrieval-Augmented Error Reasoning

Research paper

xAI · 29 AugGrok Bot now works with XCapability change

GitHub · 28 AugGitHub Copilot in Visual Studio — August update