Benchmark checker Law, finance, health, science

Is Aithos LARA still meaningful?

Status:New / unproven Checked against the report, 5 November 2026

Verdict

Unproven. It is small and has no published lawyer review of its second study.

Why new / unproven: It is the only active EU-law agent benchmark with recurring public results (single source). It covers ten scenarios and two laws.[1][1] "No one is holding the line" Aithos Single source

What “New / unproven” means

Known problems

  • It has ten scenarios, two laws and no published lawyer review of the second study.[1][1] "No one is holding the line" Aithos Single source
  • Its public data holds no Claude Opus 5.5, GPT-6 Astra or Gemini 4 Argon runs.[2][2] LARA leaderboard API Aithos Primary

What to look at instead

The report names no direct successor.

Where it appears in the report

Chapter 1, Benchmarks

Sources

Copied from the chapter source lists. Each number links back to the source in its chapter.

  1. [1]
    "No one is holding the line", Aithos. It reports LARA results for 18 models under EU law. Single source aithos.substack.com Chapter 1, source 16
  2. [2]
    LARA leaderboard API, Aithos. It returns 3,681 judged leaderboard runs on 18 models. Primary lara.aithos.org Chapter 1, source 17