Publish v2 benchmark wiki: 7 models, 23 languages (judge: claude-opus-4-7-rubric-v2-poe)
Publish v2 benchmark wiki: 7 models, 23 languages
Publish v2 benchmark wiki: 4 models, 23 languages
Archive v1 benchmark — renamed pages with Archive- prefix
Update benchmark results (benchmark_complete_v6)
Update benchmark results with translategemma:27b (benchmark_complete_v5)
Update benchmark results (benchmark_complete_v5)
Update benchmark results (benchmark_complete_v4)
Update benchmark results (benchmark_complete_v3)
Update benchmark results (benchmark_complete_v2)
Update benchmark results (benchmark_complete)
Update benchmark results (71bac225)
Update benchmark results (20251223_233607)
Update benchmark results (20251223_231903)
Update benchmark results (20251223_225649)
Update benchmark results (latest)