Fetching from the wire…
01
02
03
04
05
06
07
08
Models2026-06-23 · source-backed
As of today Fable 5 is no longer bundled at no extra cost in seat-based plans, and continued use draws on usage credits. The wrinkle: Fable 5 was offline June 12 to ~June 18 under the US export-control directive, so subscribers effectively got 4-5 of the advertised 13 free days. (Developers Digest) For daily Claude Code users this is a real cost change, the top SWE-bench Verified model (95%) is metered again, which pushes you to weigh credit burn against Opus 4.8 or open-weight options like GLM-5.2. The math just got more interesting in the open model's favor.
Each link below shares sources, entities, or timing with this story.
Every number you use to pick a harness comes from public repositories the models may have trained on. Specific Labs built the version that doesn't: tasks drawn from licensed private company codebases, including a 200K-user event app and a fintech processing over 100K bank stat...
Weeks after launch, Z.ai's open-weight GLM-5.2 now accounts for roughly 75% of all Z.ai model traffic on OpenRouter, with at least one provider serving it past 125 tokens per second (GIGAZINE, citing OpenRouter). The numbers behind the surge: an Artificial Analysis Intelligenc...
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...
Everyone spent yesterday arguing about benchmark numbers. Tencent quietly published data suggesting the numbers belong to your infrastructure, not the model. The WorkBuddy Bench leaderboard reports every model under two different agent harnesses — CodeBuddy Code and Claude Cod...
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...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.