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 |
|---|---|---|---|---|---|---|
| French → Mandarin ChineseFR · French · Français→ZH · Mandarin Chinese · 普通话 | 300 | Median 2.86 Mean 2.67 · 25th pct. 2.70 · 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 |
| Hindi → Mandarin ChineseHI · Hindi · हिन्दी→ZH · Mandarin Chinese · 普通话 | 135 | Median 6.38 Mean 6.29 · 25th pct. 6.08 · 75th pct. 6.78 | Mean 0.737 25th pct. 0.731 · Median 0.736 · 75th pct. 0.741 | Mean 0.0 25th pct. 0.0 · Median 0.0 · 75th pct. 0.0 | Mean 0.8 25th pct. 0.7 · Median 0.7 · 75th pct. 0.7 | Mean 0.026 25th pct. 0.021 · Median 0.021 · 75th pct. 0.021 |
| Spanish → Mandarin ChineseES · Spanish · Español→ZH · Mandarin Chinese · 普通话 | 120 | Median 6.50 Mean 6.41 · 25th pct. 6.24 · 75th pct. 6.70 | Mean 0.737 25th pct. 0.727 · Median 0.740 · 75th pct. 0.751 | Mean 0.0 25th pct. 0.0 · Median 0.0 · 75th pct. 0.0 | Mean 0.9 25th pct. 0.7 · Median 0.7 · 75th pct. 0.7 | Mean 0.040 25th pct. 0.024 · Median 0.024 · 75th pct. 0.040 |
| English → Mandarin ChineseEN · English→ZH · Mandarin Chinese · 普通话 | 306 | Median 2.71 Mean 2.65 · 25th pct. 2.47 · 75th pct. 2.86 | Mean 0.861 25th pct. 0.860 · Median 0.865 · 75th pct. 0.869 | Mean 0.2 25th pct. 0.0 · Median 0.0 · 75th pct. 0.0 | Mean 0.9 25th pct. 0.0 · Median 0.0 · 75th pct. 0.0 | Mean 0.029 25th pct. 0.025 · Median 0.025 · 75th pct. 0.025 |
| Portuguese → Mandarin ChinesePT · Portuguese · Português→ZH · Mandarin Chinese · 普通话 | 110 | Median 6.62 Mean 6.42 · 25th pct. 6.19 · 75th pct. 6.81 | Mean 0.736 25th pct. 0.731 · Median 0.737 · 75th pct. 0.741 | Mean 0.0 25th pct. 0.0 · Median 0.0 · 75th pct. 0.0 | Mean 0.9 25th pct. 0.7 · Median 0.7 · 75th pct. 0.7 | Mean 0.036 25th pct. 0.028 · Median 0.028 · 75th pct. 0.038 |
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.