TrueIQ.si
Submit a tool

// guides · leaderboards

Leaderboards

This topic covers the TrueIQ guides on AI leaderboards: who runs each one, what it measures, how scores are collected and where the rankings can mislead. Each guide links to the leaderboard itself and to its published method, and keeps the leaderboard's own claims separate from our reading of them.

There are 4 guides here, published from Oct 24, 2026 to Nov 14, 2026. The tools they cover most often are Artificial Analysis, Jev (TypeSafe AI) and Jev Decision Index.

How to choose: start with the guide for the leaderboard you see quoted most, then read the explainer on the benchmark it is built on. When two leaderboards disagree, the comparison guides explain why. Scores move every week, so check the last checked date and the live leaderboard before quoting a number.

  1. 9 min readListen

    SO-Arena Benchmark: How System One Models Rank

    SO-Arena tests System One decision models on 2,919 tasks in 11 domains. Who leads, why the top scorer is only seventh on reliability, and how to read it.

  2. 10 min readListen

    Jev Decision Index: How Decision Models Rank

    The Jev Decision Index ranks 275 decision models on private tests. How the Full score works, who leads, why Jev sits 55th, and how it differs from AA's index.

  3. 9 min readListen

    Harness Leaderboard: How the Harness Moves Scores

    The Harness Leaderboard runs 9 coding agent harnesses on the same open models. What v0.1.3 shows, who ties for first, what it costs, and the caveats.

  4. 10 min readListen

    Coding Agent Benchmark Rankings (October 2026)

    Coding agent benchmark rankings from SWE-Bench Pro, FrontierCode, Terminal-Bench and the Artificial Analysis index, with sourced scores, dates and why they differ.

    · updated

All 99 guides →