EuroMoE-2.6B-A0.6B-2512: benchmark results

Provider: utter-project. Access: Open.

Aggregate Rating 1199 ± 34, rank #9443 of 10552 rated models, from 26 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Lara Mini Base Report (base-model protocol) - Global PIQA (non-parallel), All Languages (0-shot)58.2Accuracy (%) averaged over all languages/variants of the ben80.6
Lara Mini Base Report (base-model protocol) - Global PIQA (parallel), All Languages (0-shot)25Accuracy (%) averaged over all languages/variants of the ben63.9
Lara Mini Base Report (base-model protocol) - T-HellaSwag, All Languages (0-shot)39Accuracy normalized by answer length (%) averaged over all l61.1
Lara Mini Base Report (base-model protocol) - PIQA (0-shot)76.8Accuracy normalized by answer length (%), English benchmark48.1
Lara Mini Base Report (base-model protocol) - XCOPA, All Languages (0-shot)55.9Accuracy (%) averaged over all languages/variants of the ben44.4
Lara Mini Base Report (base-model protocol) - XNLI, All Languages (0-shot)39.4Accuracy (%) averaged over all languages/variants of the ben43.5
Lara Mini Base Report (base-model protocol) - XNLI (English) (0-shot)52.3Accuracy (%), English benchmark33.3
Lara Mini Base Report (base-model protocol) - HellaSwag (10-shot)65Accuracy normalized by answer length (%), English benchmark29.6
Lara Mini Base Report (base-model protocol) - COPA (0-shot)79Accuracy (%), English benchmark24.1
Lara Mini Base Report (base-model protocol) - CRUXEval-I (2-shot)24.8pass@1, direct prediction, official answer parser (%)16.7
Lara Mini Base Report (base-model protocol) - WinoGrande (5-shot)61.3Accuracy (%), English benchmark16.7
Lara Mini Base Report (base-model protocol) - ARC-Challenge (25-shot)44.8Accuracy normalized by answer length (%), English benchmark14.8

Interactive version: theaggregate.ai/model?slug=euromoe-2-6b-a0-6b-2512 · How It Works · Data refreshed daily, snapshot 2026-11-16.