io.github.tjacquesson/llmtest-mcpai

llmtest-mcp

Verified · 34 days ago

Benchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models.

Install

claude mcp add llmtest-mcp -- npx -y [email protected]

Requires: LLMTEST_API_KEY

Our take

Provides model benchmarking on real prompts, with an emphasis on cost and speed comparisons across many LLMs. It is for teams evaluating model tradeoffs or looking for cheaper substitutes without building their own benchmark harness first. The utility is obvious, but benchmark quality depends heavily on prompt selection and methodology, so results should be treated as directional rather than definitive.

reviewed by hand · 2026-07-16

Something wrong or dead here? Report it

Verification record

last verified
34 days ago
github stars
0
last commit
4 mo ago
archived
no
license
MIT
downloads / wk
56
latest version
0.6.1
in registry since
2026-05-22

github.com/tjacquesson/llmtest-mcp

claude-flowai

claude-flow

Verified · 17 days ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed73k stars19k dl/wkchecked 17 days ago

tldrawai

tldraw

Verified · 18 days ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed50k starschecked 18 days ago

codebase-memory-mcpai

Codebase Memory

Verified · 8 days ago

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed45k stars12k dl/wkchecked 8 days ago

openmetadata-mcpai

OpenMetadata

Verified · today

Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.

hand-reviewed15k starschecked today

mobilerunai

mobilerun

Verified · 20 days ago

Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.

hand-reviewed9.4k starschecked 20 days ago

praisonaiai

PraisonAI

Verified · 7 days ago

AI Agents Framework with Self Reflection and MCP support

hand-reviewed9.1k starschecked 7 days ago