Domyn-Edge-Base: benchmark results

Provider: Domyn. Released 2026-10-20. Access: Open.

Aggregate Rating 1439 ± 35, rank #4368 of 10552 rated models, from 26 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Lara Mini Base Report (base-model protocol) - PAWS-X, All Languages (0-shot)63.3Accuracy (%) averaged over all languages/variants of the ben100
Lara Mini Base Report (base-model protocol) - PAWS (English) (0-shot)69.4Accuracy (%), English benchmark94.4
Lara Mini Base Report (base-model protocol) - Belebele (English) (0-shot)85.8Accuracy (%), English benchmark90.7
Lara Mini Base Report (base-model protocol) - CRUXEval-I (2-shot)42.5pass@1, direct prediction, official answer parser (%)88.9
Lara Mini Base Report (base-model protocol) - GSM8K (5-shot)74.6Exact match (strict extraction: first "#### N", else first \87
Lara Mini Base Report (base-model protocol) - Belebele, All Languages (0-shot)47.3Accuracy (%) averaged over all languages/variants of the ben85.2
Lara Mini Base Report (base-model protocol) - MBPP (3-shot)53.8pass@1 (execution) (%)84.3
Lara Mini Base Report (base-model protocol) - WinoGrande (5-shot)73.7Accuracy (%), English benchmark83.3
Lara Mini Base Report (base-model protocol) - COPA (0-shot)86.2Accuracy (%), English benchmark81.5
Lara Mini Base Report (base-model protocol) - MGSM (8 (CoT)-shot)47Exact match on each language's native CoT answer phrase, ave79.6
Lara Mini Base Report (base-model protocol) - MBPP+ (3-shot)55.8pass@1; must pass MBPP's own and the EvalPlus tests (%)78.7
Lara Mini Base Report (base-model protocol) - CRUXEval-O (2-shot)37.3pass@1, direct prediction, official answer parser (%)76.9

Interactive version: theaggregate.ai/model?slug=domyn-edge-base · How It Works · Data refreshed daily, snapshot 2026-11-16.