EuroEval
Compare generative tasks across 32 European languages, with mean rank scores and 95% confidence intervals separated by split and prompting method.
Source & report coverage
- Source type
- Multilingual benchmarks
- Report snapshots
- 8 reports
- Data as of
- 2026-10-28
Sources and individual reports are listed separately. Each snapshot retains its subjects, tasks, metrics and conditions. External scores are not our own measurements and are not added across reports.
Reports & historical snapshots
- EuroEval European languages · Test split · few-shot →
Observed2026-10-28 · 474subject / run records ·33independent metrics
- EuroEval European languages · Test split · zero-shot →
Observed2026-10-28 · 40subject / run records ·33independent metrics
- EuroEval European languages · Validation split · few-shot →
Observed2026-10-28 · 181subject / run records ·33independent metrics
- EuroEval European languages · Validation split · zero-shot →
Observed2026-10-28 · 92subject / run records ·33independent metrics
- EuroEval European languages · Test split · few-shot →
Observed2026-10-18 · 469subject / run records ·33independent metrics
- EuroEval European languages · Test split · zero-shot →
Observed2026-10-18 · 37subject / run records ·33independent metrics
- EuroEval European languages · Validation split · few-shot →
Observed2026-10-18 · 181subject / run records ·33independent metrics
- EuroEval European languages · Validation split · zero-shot →
Observed2026-10-18 · 90subject / run records ·33independent metrics