Benchmark
Third version of the Terminal-Bench suite, which scores AI models on agentic tasks carried out in a command-line terminal; used to compare coding agents.
Flash's off-peak input price is under a quarter of what V4-Pro cost, and on DeepSeek's own table it beats the old Pro checkpoint on Terminal-Bench, but it scores 36.8 on Humanity's Last Exam and no V4.1-Pro has a date.
Reality
The framework separates configuration choices that move a deployment along a latency and throughput frontier from advances that move the frontier itself, which is the distinction you need before trusting anyone's benchmark table.
Reality
The 5 trillion token ceiling only binds if every allocation is claimed and then spent. Until it is, this is a short window to test a rival coding agent on someone else's inference bill.
Reality
Z.ai says its new model tops CyberGym and leads open-source models on Terminal Bench 3.0. The weights go to Hugging Face within two weeks, which is the part security teams should read twice.
Reality
Z.ai says its 743B-parameter GLM-5.3 hits 34.5% on its own code bench using 22% fewer output tokens than GLM-5.2. The weights are still two weeks out.
Reality
Z.ai's August 14 post claims post-training gains for coding agents, but the company's release notes still stop at GLM-5.1 and there is no API endpoint, model identifier or weight download.
Reality
Z.ai says all of GLM-5.3's coding gains came from post-training on tenfold more long-horizon task environments. The uneven benchmark jumps tell you where that money actually landed.
Reality