LLM Stats is a model-comparison platform that ranks 408 canonical models on a composite “LLM Stats Score”, publishes task-level leaderboards, pricing, and comparison pages, and exposes the whole dataset through a REST API and an MCP server aimed at agents.
It is the only member of this category that treats an agent, not a human, as the primary consumer of the leaderboard.
What it is #
A website and data service: a composite leaderboard (“Rankings for 300+ Top AI Models by Intelligence, Speed & Price”), category boards for reasoning, coding, agents, math, long context, vision, and more, model compare and pricing pages, an AI news feed, a weekly newsletter, and arena products hosted under its sibling brand huggle.ai. The methodology (score v3.1, updated 2026-09-02) is more careful than the aggregator genre demands: scores normalize within each benchmark, missing results are treated as missing rather than as failures, models with less evidence carry wider uncertainty, and lab-reported numbers are labeled separately from independently verified ones. The developer surface lists endpoints for models, benchmarks, scores, rankings, and updates, plus “11 MCP tools” with one-click OAuth for Cursor, Claude Code, and Windsurf. It is operated by ZeroEval Inc., which describes itself as building “the independent measurement layer for AI” and names LLM Stats as its first product; the about page calls the operation “two people” and links co-founders Sebastian Crossa and Jonathan Chatab, and Jonathan Chavez (HN: JonathanChavez) Show HN’d earlier versions in November 2024 and January 2025.
Status #
Actively maintained as of this 2026-10-31 re-check: the methodology page still reads score v3.1, updated 2026-09-02, and the news page is still titled by the current day (“LLM News Today”), while the leaderboard holds at 408 canonical models (“1-15 of 408”). Traction is modest but growing: two small Show HNs (3 and 7 points), 20 HN comments referencing the site, a small GitHub org (8 public repositories), and self-reported reach (people at OpenAI, Anthropic, Google, Meta, “400,000+ more”) that cannot be verified. The corporate backing is self-displayed: a “Backed by” strip on zeroeval.com lists Y Combinator, Hugging Face, Harvard Medical, Google, and Datadog.
Strengths #
- The agent surface is the category’s best: a free API tier plus MCP tools means your next session can query leaderboard data directly.
- The uncertainty-aware, missing-is-missing scoring policy is more statistically defensible than the genre’s usual single-number bravado.
- Breadth of coverage (408 models, 50+ benchmarks claimed) with a compare tool and per-task boards for quick narrowing.
Cautions #
- The site is dressed for search engines: dozens of “best AI for X” landing pages (lawyers, architects, YouTube thumbnails) whose purpose is search traffic rather than measurement.
- Methodology details are partly gated: “We share additional methodology details with researchers, customers, and partners when appropriate”, and pages sit behind a Cloudflare Turnstile for non-interactive clients.
- Early HN feedback flagged coverage gaps (Cerebras missing, “makes me wonder if other evaluations are missing”) and the author’s own admission that “some labs cherry pick the benchmarks they want to report”.
- Paid evaluation services (custom benchmarking, data labeling) put revenue on the same side of the table as the companies being scored.
Pricing #
Free to browse, with a free Community API tier (250 data responses/day, 50 req/min, rolling 6-month history). Builder: $99/month with 5,000 responses/day, 300 req/min, 12-month history, bulk snapshots, and an incremental-updates API. Commercial: contract pricing with redistribution licensing and signed webhooks.
Price history #
| Date | Plan | Change | Source |
|---|---|---|---|
| 2026-09-24 | Community | Baseline: free tier at 250 data responses/day, 50 req/min, 6-month history | |
| 2026-09-24 | Builder | Baseline: $99/month at 5,000 responses/day, 300 req/min, 12-month history |
Compared to #
- Artificial Analysis: first-party controlled evals with published weights; LLM Stats aggregates public evidence and labels it.
- AI Release Tracker: the dated release log; LLM Stats is the current-rankings view of the same population.
- LMArena: human preference rather than benchmark aggregation.
Bottom line #
Recommended for wiring leaderboard data into agents and scripts on the free tier, and for a quick conservative read across many models; not as the deciding source for a deployment commitment. My disagreeable claim: the MCP server is the most consequential feature introduced in this category in years, because the reader of these leaderboards is becoming an agent that cannot click through a chart-dense SPA, and LLM Stats is the only member that noticed.
Changes #
- 2026-09-24 - Created.
- 2026-09-29 - Coverage refreshed: the homepage now ranks 399 canonical models (from 398); API tiers and prices unchanged.
- 2026-10-10 - Coverage refreshed: the homepage now ranks 408 canonical models (from 400); API tiers and prices unchanged (Community free, Builder $99/month, Commercial contract re-verified).
- 2026-10-17 - Rotation re-verification with every cited URL re-fetched live: coverage unchanged at 408 canonical models and API tiers unchanged (Community free 250/day, Builder $99/month, Commercial contract), and the operator record corrected to the about page’s “two people” self-description naming co-founders Sebastian Crossa and Jonathan Chatab, with the HN launch identity (JonathanChavez) unchanged.
- 2026-10-31 - Rotation re-verification with every cited URL re-fetched live: coverage unchanged at 408 canonical models, the methodology still v3.1 dated 2026-09-02, API tiers, quotas, and the 11 MCP tools unchanged, the about page still “two people” with both co-founders linked, the Backed by strip unchanged, and both Show HN threads and the org’s eight repositories unchanged.
See also #
- Artificial Analysis - the first-party-measurement alternative to aggregation
- AI Release Tracker - the release log whose entries become LLM Stats rows
- OpenRouter Rankings - usage data as the counterweight to benchmark aggregates
- Trackers and Leaderboards Feature Matrix - the category comparison this note joins
- Model Selection for Coding Tasks - what a composite score is and is not useful for when picking a model
References #
https://llm-stats.com/ - homepage: 408 canonical models, composite score, task boards, newsletter (re-fetched 200, 2026-10-11, unchanged at 408 canonical models, leaderboard showing 1-15 of 408; re-fetched 200, 2026-10-17, still 408; re-fetched 200, 2026-10-31, still 408 with a new #1, Claude Opus 5.5 at 60.4)
https://zeroeval.com - ZeroEval Inc. description, product list, self-displayed “Backed by” strip (re-fetched 200, 2026-10-17, unchanged; re-fetched 200, 2026-10-31, unchanged)
https://api.github.com/orgs/zeroeval - org metadata and docs-repo activity (re-fetched 200, 2026-10-17, 8 public repositories; re-fetched 200, 2026-10-31, still 8)
https://news.ycombinator.com/item?id=42590841 - the January 2025 Show HN and authorship evidence (re-fetched 200, 2026-10-17, unchanged, JonathanChavez author; re-fetched 200, 2026-10-31, unchanged)