llm2014/llm_benchmark resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1567 stars · 22 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A personal, long-running benchmark that tracks large language model performance on logic, math, programming, and intuition tasks using a private, rolling question bank of ~28 questions. Results are published as a monthly leaderboard with scoring based on multi-point rubrics.

Use cases

• compare reasoning ability of different LLMs
• track how LLMs improve over time
• find which model is best at math and logic puzzles
• view a leaderboard of large language model scores
• evaluate models on programming and deduction tasks

When to choose

• you want an independent, long-term view of LLM reasoning trends
• you need a leaderboard covering logic, math, and coding ability
• you want to see how specific models evolve month over month

When to avoid

• you need a comprehensive or authoritative academic benchmark
• you require publicly available test questions to run yourself
• you need domain-specific evaluation outside reasoning tasks

Facets

dataset · maturity active

benchmarking llm-inference large-language-models artificial-intelligence machine-learning python llm-evaluation leaderboard private-question-bank reasoning-benchmark monthly-updates chinese-language evaluation web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="llm2014/llm_benchmark")