01fish-llm-radar

Community

Benchmark OpenAI-compatible LLMs in 30 minutes.

AuthorOrangeViolin
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Benchmark OpenAI-compatible LLMs across seven objective tests to help teams compare models quickly and reproducibly.

Core Features & Use Cases

  • One-shot benchmarking across GSM8K, MATH, MMLU, MMLU-Pro, C-Eval, IFEval, HumanEval for a broad capability snapshot.
  • Multi-model horizontally comparative evaluation across providers (DeepSeek, OpenRouter, SiliconFlow, Volces, self-hosted endpoints).
  • Transparent data provenance with per-sample results and aggregated summaries, plus deep analysis reports.

Quick Start

Install dependencies, configure API keys, and run a sample evaluation with a chosen model and benchmark.

Dependency Matrix

Required Modules

openaidatasetspython-dotenvtqdm

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: 01fish-llm-radar
Download link: https://github.com/OrangeViolin/01fish-llm-radar/archive/main.zip#01fish-llm-radar

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.