Model capability radar plugin for the DeepSeek Harness Web GUI
-
Updated
Sep 14, 2026 - TypeScript
#
model-benchmark
Here are 8 public repositories matching this topic...
Public report and aggregate evidence for LayerRail's July 2026 frontier-model deployment study
-
Updated
Jul 30, 2026
This script cleans passenger data, creates family features, tests eight models including XGBoost and CatBoost, and combines their votes to predict survival.
-
Updated
Feb 25, 2026 - Python
Native macOS menu-bar watcher for AI Stupid Level: top 20, value rankings, GPT/Claude clusters, C/R/T signals, and a notch island.
macos swift ai leaderboard openai gpt model-evaluation notch claude swiftui menubar-app llm model-benchmark model-ranking aistupidlevel
-
Updated
Aug 14, 2026 - Swift
Tariff comparison tool for Mistral Large 4 users — track usage limits across plans.
desktop-app windows utility gui mistral-ai llm-pricing model-benchmark ai-cost-calculator mistral-large-4 tariff-comparator
-
Updated
Sep 8, 2026 - HTML
End-to-end Deep Learning Vision Benchmark evaluating 11 architectures across 5 paradigms. Features Soft-Voting Ensemble (98.92% Top-5), ONNX INT8 Quantization (3.01x speedup), Grad-CAM XAI, FastAPI microservice, and live Streamlit Arena.
python docker computer-vision deep-learning grad-cam pytorch ensemble-learning resnet quantization strea xai fastapi streamlit onnx-runtime vision-transformer convnext effientnet model-benchmark
-
Updated
Sep 17, 2026 - Python
Healthcare demand forecasting and staffing decision platform (PoC): a 13-model benchmark (baselines, SARIMAX, Prophet, global gradient boosting, Nixtla Stats/ML/Neural, Chronos), conformal prediction intervals, rolling-origin backtesting, a costed staffing layer, batch pipeline, FastAPI serving, monitoring and responsible-ML docs.
python data-science machine-learning time-series scikit-learn healthcare xgboost forecasting lightgbm uncertainty-quantification prophet sarimax portfolio-project time-series-forecasting conformal-prediction mlops fastapi nixtla staffing-optimization model-benchmark
-
Updated
Sep 9, 2026 - Jupyter Notebook
Ask one question to multiple LLMs simultaneously — auto-discovers configured models, parallel calls, side-by-side comparison
side-by-side multi-model zero-config model-discovery prompt-testing ollama llm-evaluation dashscope llm-comparison agent-skills openai-compatible provider-agnostic model-benchmark parallel-query answer-comparison
-
Updated
Sep 19, 2026
Add this topic to your repo
To associate your repository with the model-benchmark topic, visit your repo's landing page and select "manage topics."