Fetching from the wire…
01
02
03
04
05
06
07
08
Models2026-08-21 · source-backed
The 397B MoE scores 86.1 on Terminal-Bench 2.1 (Terminus-2) against Claude Opus 4.8's 85.0, 86.0 on SWE-bench Verified, and 92.8 on GPQA Diamond. Hugging Face But it trails badly on the harder agentic rows: 13.5 versus 21.1 on Frontier-Bench v0.1, 59.5 versus 69.7 on NL2Repo. All numbers are vendor-reported and averaged over five runs. The parity claim rests entirely on the 397B, and the gap on long-horizon agentic work is where I'd expect the difference to actually bite. Weights for every size are downloadable, unlike GLM-5.3.
Each link below shares sources, entities, or timing with this story.
This is the other half of the Fable 5 story, so read them together. While the best coding model in the world is uncallable, an open-weight one quietly posted frontier-adjacent numbers. Per Tom's Hardware, independent benchmarks for the MIT-licensed GLM-5.2 (744B params, 40B ac...
Z.ai's GLM-5 (744B/40B MoE, MIT license, 205K context) is free on NVIDIA NIM at 40 req/min with no credit card. Benchmarks: 77.8% SWE-bench Verified (highest open-source), 56.2 Terminal-Bench 2.0 (approaching Opus 4.5's 59.3). Trained entirely on 100,000 Huawei Ascend chips. Y...
Martin Alderson's essay "The upcoming AI margin collapse, part 1: GLM 5.2" hit 675 points and 462 comments on Hacker News, and it's the rare HN chart-topper that's actually about spreadsheet math instead of vibes. The argument is simple. Z.ai's GLM 5.2 delivers frontier-adjace...
Moonshot AI dropped Kimi K2.6 today and the numbers are hard to ignore. One trillion parameters total, 32 billion active per token across 384 experts, 256K context window, and native multimodal input. It scores 58.6 on SWE-Bench Pro versus GPT-5.4's 57.7 and Claude Opus 4.6's...
Alibaba released Qwen3.6-27B on April 22. Dense architecture. Open weights. 77.2% on SWE-bench Verified, within 3.7 points of Claude Opus 4.6. On SkillsBench, it scores 48.2% versus its own 397B MoE predecessor's 30.0%. That's a 77% improvement with 14.8x fewer parameters. Let...
GLM-5.1 from Zhipu AI scored 58.4% on SWE-bench Pro. GPT-5.4 scored 57.7%. Claude Opus 4.6 scored 57.3%. That's the first time an open-weight model has ever topped a major coding benchmark against the best proprietary models. The specs matter. GLM-5.1 is a 754B-parameter mixtu...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.