Loading benchmarks…
Automated translation metrics summarized for 334 language directions.
Sources — Source segments come from curated, public-facing parallel corpora and benchmark-style collections mixed for broad coverage. They are not model-generated: originals and references are assembled upstream as parallel text only; this dashboard does not redistribute raw corpora.
Mixed parallel corpora — Parallel segments spanning diverse genres and corpus scales. Each item includes a reference translation that is certified and human-verified—not produced by the models being benchmarked.
Language pairi | Rankingi | Fluencyi | COMETi | BLEUi | sacreBLEUi | Len ratioi |
|---|---|---|---|---|---|---|
| English → ThaiEN · English→TH · Thai · ไทย | 1 | Mean 2.84 25th pct. 2.86 · Median 2.86 · 75th pct. 2.86 | Mean 0.937 25th pct. 0.922 · Median 0.925 · 75th pct. 0.956 | Mean 0.0 25th pct. 0.0 · Median 0.0 · 75th pct. 0.0 | Mean 0.0 25th pct. 0.0 · Median 0.0 · 75th pct. 0.0 | Mean 0.198 25th pct. 0.170 · Median 0.170 · 75th pct. 0.198 |
| French → Mandarin ChineseFR · French · Français→ZH · Mandarin Chinese · 普通话 | 2 | Mean 2.67 25th pct. 2.70 · Median 2.86 · 75th pct. 2.86 | Mean 0.856 25th pct. 0.853 · Median 0.859 · 75th pct. 0.861 | Mean 0.0 25th pct. 0.0 · Median 0.0 · 75th pct. 0.0 | Mean 0.0 25th pct. 0.0 · Median 0.0 · 75th pct. 0.0 | Mean 0.018 25th pct. 0.018 · Median 0.018 · 75th pct. 0.018 |
| Russian → UzbekRU · Russian · Русский→UZ · Uzbek · Oʻzbek | 2 | Mean 5.09 25th pct. 4.74 · Median 5.19 · 75th pct. 5.45 | Mean 0.817 25th pct. 0.816 · Median 0.822 · 75th pct. 0.825 | Mean 5.7 25th pct. 5.1 · Median 5.7 · 75th pct. 6.2 | Mean 8.7 25th pct. 8.2 · Median 8.7 · 75th pct. 9.2 | Mean 1.026 25th pct. 1.014 · Median 1.025 · 75th pct. 1.040 |
| English → TamilEN · English→TA · Tamil · தமிழ் | 4 | Mean 5.11 25th pct. 4.73 · Median 4.98 · 75th pct. 5.39 | Mean 0.867 25th pct. 0.855 · Median 0.871 · 75th pct. 0.877 | Mean 5.1 25th pct. 4.5 · Median 5.0 · 75th pct. 5.5 | Mean 10.9 25th pct. 9.8 · Median 11.0 · 75th pct. 11.6 | Mean 0.777 25th pct. 0.767 · Median 0.781 · 75th pct. 0.791 |
| Spanish → UkrainianES · Spanish · Español→UK · Ukrainian · Українська | 4 | Mean 6.46 25th pct. 5.81 · Median 6.28 · 75th pct. 7.14 | Mean 0.877 25th pct. 0.869 · Median 0.879 · 75th pct. 0.884 | Mean 23.6 25th pct. 23.2 · Median 24.8 · 75th pct. 26.6 | Mean 31.5 25th pct. 30.8 · Median 32.5 · 75th pct. 34.0 | Mean 0.926 25th pct. 0.912 · Median 0.918 · 75th pct. 0.931 |
This release reports translation quality by language pair: medians and spread of automated scores (fluency, COMET, BLEU, sacreBLEU, length ratio) aggregated across evaluated directions. Run metadata describes recipes, metrics, and segment counts.