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” meansKnown problems
What to look at instead
The report names no direct successor.
Where it appears in the report
Chapter 1, Benchmarks
- Domain benchmarks test expert skill, not lawful conduct
- Figure 11. Few benchmarks test conduct under a named law
- Table 10. EU law, regulation and privacy benchmarks by tier: mapping, assessment or conduct, November 2026 in “Go deeper: EU law, regulation and privacy benchmarks (8)”
Sources
Copied from the chapter source lists. Each number links back to the source in its chapter.
- [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] LARA leaderboard API, Aithos. It returns 3,681 judged leaderboard runs on 18 models. Primary lara.aithos.org Chapter 1, source 17