Spec Kitty ran 12 open-weight models through the SWE-bench benchmark (with a little help…
This is a dev post classified by AGK Intelligence as AI dev tools (news), kept by the Dev Radar because it carries real work, not commentary.
Spec Kitty ran 12 open-weight models through the SWE-bench benchmark (with a little help from https://exe.dev): https://spec-kitty.ai/blog/benchmarking-open-weight-models-swe-bench
Posted by exe.dev (3.8k followers) 1 h ago · 6 likes · 501 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: exe.dev.
More dev work like this
- 🤯天呐！GPT-6 Astra 居然直接“手改” 开源权重，Qwen3.5-0.8B小模型数学能力提升近6倍！无训练、无梯度！ — @NFT_Chen
- The #TauCeti project is using AI to build a library of formalized mathematics:… — @leanprover
- Meet Audio8-TTS-Realistic-Air: a text-to-speech model that clones voices from just a few… — @HuggingModels
- 🚨重磅预警！腾讯混元Hy4正式版即将上线！ 视觉能力首次上车，部署信号已亮起！ — @NFT_Chen
- Tencent released a new research-agent harness. It's not being used as you might think. — @TeksEdge
- You can now Run Uncensored DeepSeek-V4.1-Flash- — @0x0SojalSec
- Meet DeepSeek-V4.1-Flash-1017-GGUF: a quantized text-generation model ready for your… — @HuggingModels
- You can run locally Uncensored DeepSeek-V4.1-Flash-1017 on a 12GB GPU on consumer… — @0x0SojalSec
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 9k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-02 19:42 UTC. Full method.