The Multivac
Which LLM thinks best? Blind peer-judged leaderboard.
The Multivac launched on May 3, 2026 with 4 votes, #2,419 of 20,538 launches that month and more than 75% of that year's launches.
What it does
Most LLM leaderboards are static, gameable, or judged by a single model. The Multivac runs a 10×10 blind peer matrix: every frontier model answers, then judges every other model's answer without knowing whose it is. What you get is a ranking of reasoning quality, not memorized benchmarks. Features: Ask Multivac (live multi-model answers + share pages), Model Pulse heatmap, head-to-head Compare, full data export, and an open-source evaluation engine (MIT).
Every question independently routed to the top-ranked model in the Multivac eval. Open data. No lock-in.
Every question is independently routed to the model ranked highest for that category by the live evaluation stream. Routing uses live raw means; it does not assert a statistically separated winner (see paper §5.1). Open data. Nofrom app.themultivac.com
Does a similar job
all alternatives →
LLM StatsOct 2025 · llm-stats.com · ▲293I was overspending on GPT-4o. It was really hard to compare different models I could switch to, so I built this LLM comparison tool. It shows leaderboards, pricing, and performance data across 100+ LLMs (including all major providers and open-source models). Key features: - Live pricing comparisons - Benchmark Scores (MMLU, HumanEval, GPQA, etc.) - Context length vs cost analysis - Speed/throughput tests across providers - Quality vs price visualizations - Open source (all data verifiable) Try it out: https://llmstats.com I'd like to know your opinion :) Tech stack: Next.js,…
How I topped the HuggingFace open LLM leaderboard on two gaming GPUsMar 2026 · dnhkng.github.io · ▲495I 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…
QuickCompare by TrismikApr 2026 · trismik.com · ▲231Compare LLMs on your data, measure, and pick the best.
Find the best local LLM for your hardware, ranked by benchmarksMay 2026 · github.com · ▲283Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly. - Andyyyy64/whichllm
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com