Skip to content
ReviewRamble

The weekly brief

AI, reviewed, in your inbox.

  • New reviews of tools, models, MCP servers and repos, with the verdict up front
  • Re-checked prices and ratings when something changes
  • New analysis pieces as they are published

Models, agents, MCP servers and the tools actually worth your time.

One email a week. Unsubscribe with the link in any brief. How we use your email

Leaderboard (AI)

An AI leaderboard is a public ranking of models by their scores on one or more benchmarks or on human preference votes, updated as new models are tested, so readers can compare models side by side.

Also called: arena, LLM leaderboard, model leaderboard

By Divya Sharma · Checked Nov 15, 2026 · How we review

Leaderboards turn benchmark results into a table. Some rank models on a single AI benchmark, such as a coding or embedding test. Some combine many benchmarks into one index, like the Artificial Analysis Index. Others, called arenas, rank models by how often people prefer their answers in blind side-by-side comparisons.

Arenas

The best known is Chatbot Arena (see LMArena). Users chat with two anonymous models and vote for the better reply. The paper describing it explains that it uses pairwise comparison and crowdsourced votes, and that it had become one of the most referenced LLM leaderboards. Votes are turned into scores with an Elo-style rating. Arenas capture what people like in open-ended chat, which fixed tests miss, but they also reward style, length and formatting.

How to read one

Check what is being measured and who ran the tests: the leaderboard's maintainers, or the model makers reporting their own numbers. Look at confidence intervals; models a few points apart are often statistically tied. Check the date, since rankings change quickly. Be wary of benchmark contamination and of models tuned to a leaderboard's format.

Our own rankings collect public scores per task. Treat any leaderboard as a starting shortlist, then test the top few on your own data.

Related terms

AI benchmark
An AI benchmark is a fixed, public set of tasks with an agreed scoring method, used to compare models on the same test, for example coding issues solved, exam questions answered or retrieval quality across many datasets.
Elo rating (model arenas)
An Elo rating, in model arenas, is a score computed from many head-to-head votes between pairs of models, so that the gap between two scores predicts how often one model's answer will be preferred over the other's.
LMArena
LMArena, first known as Chatbot Arena, is a public platform that ranks AI models by crowdsourced human votes: users see two anonymous models answer the same prompt and pick the better response.
Artificial Analysis Intelligence Index
The Artificial Analysis Intelligence Index is a composite score from the benchmarking company Artificial Analysis that combines several evaluations, spanning knowledge work, coding, science and general knowledge, into one number for comparing language models.
Benchmark contamination
Benchmark contamination is when a model has seen a benchmark's test questions or answers during training, so its score on that benchmark overstates how well it handles new problems of the same kind.

Sources