Alternatives
Products that do what Top Aiz does
The most minimal LLM leaderboard
- 1
Compare LLMs on your data, measure, and pick the best.
Apr 2026 · trismik.com
- 2
- 3
- 4FT
May 2026 · github.com
- 5HI
I found that duplicating a specific block of 7 middle layers in Qwen2-72B, without modifying any weights, improved performance across all Open LLM Leaderboard benchmarks and took #1. As of 2026, the top 4 models on that leaderboard are still descendants. The weird finding: single-layer duplication does nothing. Too few layers, nothing. Too many, it gets worse. Only circuit-sized blocks of ~7 layers work. This suggests pretraining carves out discrete functional circuits in the layer stack that only work when preserved whole. The whole thing was developed on 2x RTX 4090s in my basement. I'm…
Mar 2026 · dnhkng.github.io
- 6
- 7IS
Hello HN, I'm Ghita, co-founder of ZeroEntropy (YC W25). We build high accuracy search infrastructure for RAG and AI Agents. We just released two new state-of-the-art rerankers zerank-1, and zerank-1-small. One of them is fully open-source under Apache 2.0. We trained those models using a novel Elo score inspired pipeline which we describe in detail in the blog attached. In a nutshell, here is an outline of the training steps: * Collect soft preferences between pairs of documents using an ensemble of LLMs. * Fit an ELO-style rating system (Bradley-Terry) to turn pairwise comparisons into…
2025 · zeroentropy.dev
- 8
- 9
- 10
- 11
- 12AS
Jan 2026 · skills.sh
- 13
- 14FT
2024 · github.com
- 15TL
2023 · tinyllms.vercel.app
- 16
- 17
- 18
- 19PE
Nowadays, a common AI tech stack has hundreds of different prompts running across different LLMs. Three key problems: - Choices, picking from 100s of LLMs the best LLM for that 1 prompt is gonna be challenging, you're probably not picking the most optimized LLM for a prompt you wrote. - Scaling/Upgrading, similar to choices but you want to keep consistency of your output even when models depreciate or configurations change. - Prompt management is scary, if something works, you'll never want to touch it but you should be able to without fear of everything breaking. So we launched Prompt…
2024 · jigsawstack.com
- 20
- 21
- 22
- 23
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →