Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

Comenzar

model-benchmark

Estrellas5

Forks0

Actualizado20 de abril de 2026 a las 10:12

Runs benchmark suites against models, tracks ELO rankings, manages A/B tests, and generates performance reports.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

47network

47network/Sven

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Científicos de datosOcupaciones informáticas y matemáticas·SOC 15-2051

Explorador de archivos

2 archivos

SKILL.md

readonly

name	model-benchmark
description	Runs benchmark suites against models, tracks ELO rankings, manages A/B tests, and generates performance reports.
version	0.1.0
publisher	acmecorp
handler_language	typescript
handler_file	handler.ts
inputs_schema	{"type":"object","properties":{"action":{"type":"string","enum":["list_suites","create_run","complete_run","leaderboard","report","record_elo","ab_results"]},"suite_id":{"type":"string"},"model_id":{"type":"string"},"model_name":{"type":"string"},"run_id":{"type":"string"},"winner_id":{"type":"string"},"loser_id":{"type":"string"},"is_draw":{"type":"boolean"}},"required":["action"]}
outputs_schema	{"type":"object","properties":{"result":{"type":"object"}}}

model-benchmark

Evaluates model performance with standardised benchmark suites, ELO-style rankings, A/B testing, and cost/quality/speed reporting. Provides a leaderboard and per-model deep-dive reports.

Más de este repositorio

mismo repositorio

agent-messenger

47network/Sven

Sends messages between agents, broadcasts to channels, and retrieves message history for inter-agent communication.

2026-04-205

agent-spawner

47network/Sven

Spawns, manages lifecycle, and terminates autonomous AI agents from the 40+ built-in agent catalog.

2026-04-205

context-engineer

47network/Sven

Optimize prompts and context windows to reduce token usage while preserving quality.

2026-04-205

desktop-companion

47network/Sven

Animated desktop character state machine for Sven's Tauri companion app. Manages character form (ORB, ARIA, REX, ORION), state transitions (idle→thinking→speaking→celebrating), walk cycles, thought bubbles, sound effects, and real-time agent event sync.

2026-04-205

llm-council

47network/Sven

Multi-model deliberation system. Sends queries to multiple LLMs simultaneously, has them peer-review each other's responses anonymously, then a chairman model synthesizes the best answer. Supports configurable council composition, voting strategies, and cost tracking.

2026-04-205

micrograd

47network/Sven

Interactive educational autograd engine — port of Karpathy's micrograd. Build, train, and visualise tiny neural networks step-by-step to learn how backpropagation works.

2026-04-205

name	model-benchmark
description	Runs benchmark suites against models, tracks ELO rankings, manages A/B tests, and generates performance reports.
version	0.1.0
publisher	acmecorp
handler_language	typescript
handler_file	handler.ts
inputs_schema	{"type":"object","properties":{"action":{"type":"string","enum":["list_suites","create_run","complete_run","leaderboard","report","record_elo","ab_results"]},"suite_id":{"type":"string"},"model_id":{"type":"string"},"model_name":{"type":"string"},"run_id":{"type":"string"},"winner_id":{"type":"string"},"loser_id":{"type":"string"},"is_draw":{"type":"boolean"}},"required":["action"]}
outputs_schema	{"type":"object","properties":{"result":{"type":"object"}}}

model-benchmark

Evaluates model performance with standardised benchmark suites, ELO-style rankings, A/B testing, and cost/quality/speed reporting. Provides a leaderboard and per-model deep-dive reports.