Loading benchmarks…
Benchmark dashboard
Automated translation metrics summarized for 335 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 | 303 | Median 4.78 Mean 4.26 · 25th pct. 3.37 · 75th pct. 5.00 | Mean 0.881 25th pct. 0.873 · Median 0.886 · 75th pct. 0.890 | 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 | 120 | Median 7.70 Mean 6.48 · 25th pct. 6.53 · 75th pct. 8.07 | Mean 0.737 25th pct. 0.732 · Median 0.736 · 75th pct. 0.741 | Mean 0.2 25th pct. 0.0 · Median 0.0 · 75th pct. 0.2 | 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 | 99 | Median 7.85 Mean 6.58 · 25th pct. 6.90 · 75th pct. 8.14 | Mean 0.739 25th pct. 0.731 · Median 0.743 · 75th pct. 0.751 | Mean 0.2 25th pct. 0.0 · Median 0.0 · 75th pct. 0.3 | Mean 0.9 25th pct. 0.7 · Median 0.7 · 75th pct. 0.7 | Mean 0.041 25th pct. 0.024 · Median 0.024 · 75th pct. 0.040 |
| English → Mandarin ChineseEN · English→ZH · Mandarin Chinese · 普通话 | 306 | Median 4.47 Mean 4.03 · 25th pct. 3.81 · 75th pct. 5.00 | Mean 0.885 25th pct. 0.868 · Median 0.893 · 75th pct. 0.900 | Mean 0.3 25th pct. 0.0 · Median 0.0 · 75th pct. 0.0 | Mean 1.1 25th pct. 0.0 · Median 0.0 · 75th pct. 0.0 | Mean 0.029 25th pct. 0.026 · Median 0.026 · 75th pct. 0.026 |
| Portuguese → Mandarin ChinesePT · Portuguese · Português→ZH · Mandarin Chinese · 普通话 | 110 | Median 7.78 Mean 6.64 · 25th pct. 6.72 · 75th pct. 8.23 | Mean 0.737 25th pct. 0.731 · Median 0.738 · 75th pct. 0.742 | Mean 0.2 25th pct. 0.0 · Median 0.0 · 75th pct. 0.1 | Mean 0.8 25th pct. 0.7 · Median 0.7 · 75th pct. 0.7 | Mean 0.036 25th pct. 0.028 · Median 0.028 · 75th pct. 0.041 |
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.