coding-benchmark

Lynn GitHub 镜像仓 · Qwen3.8-27B Coder390 EfficientThink 本地 GGUF（llama.cpp Q2/Q3，内置 Q4 MTP）· 主仓 https://github.com/MerkyorLynn/Lynn · 下载 https://download.merkyorlynn.com/download.html

Pokedex benchmark for LLMs

Benchmark of local LLMs (Qwen 3.6, Gemma 4) vs ChatGPT and Gemini on coding tasks. Apple M5, 32GB. Methodology, raw outputs, judge prompts, scores, and charts.

Studiobook — SHIP's open benchmark fixture: a studio class-booking SaaS (Next.js) with seeded SDLC benchmark tasks

Saotri Bench — coding benchmark for evaluating LLM agents on multi-phase programming tasks with hidden requirements.

面向 AI IDE / 编码 Agent 的编程能力基准测试框架，内置防背题三防线：公私用例分离、泛化差距检测、参数化生成

31 local and hosted LLMs tested with one difficult falling-block browser game prom31 local and hosted LLMs tested with one difficult falling-block browser game prompt. Runnable outputs and hands-on findings.pt. Runnable outputs and hands-on findings.

What extra reasoning buys in code and tests: 216 Sol coding attempts, MVCC defect detection, DAG execution, effort premiums and API-equivalent USD, with a reproducible stand and English report.

Contamination-proof LLM benchmark: fresh, verified coding tasks every run, impossible to benchmaxx

Benchmark and tune every locally installed Ollama model on your own GPUs. Finds the best model per GPU setup plus its optimal temperature and context, with a no-spill VRAM guard, coding + agentic test suites, and a single-file HTML report. 100% local: no cloud, no API keys, no model judges.

Raw logs of Claude Code running on local Qwen3.5-27B (llama.cpp). Builds a Python todo app with 50 tests. Real-world performance data: 30 min, cache thrashing, 38 t/s generation.