Benchmark Almanac

AlexandriaX 2026

cepin + Gemma 4 31B IT 32.5 tops its leaderboard
Not in model cards

Models translate English dialogue into 13 Arabic varieties, translate financial text between six dialects and mark translation errors across five varieties.

Thakaa ran NileChat on the blind dialogue test. Organizers rank dialogue translation, financial translation and error detection separately.

Released
May 2026
Kind
Translation
Level
University
Scored
Checked automatically
Answers
Open-ended
Tasks
Public, plus a private test set
Measures
Capability
Language
English, Arabic
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
Based on
Alexandria
In views
Law and finance
3
Entries on its own leaderboard, 0 models we track

cepin + Gemma 4 31B IT tops the leaderboard with 32.5 No scores yet

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as cepin + Gemma 4 31B IT, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.

  1. 1 cepin + Gemma 4 31B IT Unconstrained dialogue translation 32.5
  2. 2 NileChat-3B-Base Constrained dialogue translation 30.4
  3. 3 FCDS + Gemma 3 4B Constrained dialogue translation 26.5

Source: Official AlexandriaX 2026 leaderboard

#EntryScoreSettingSubmitted byDateSource
1 cepin + Gemma 4 31B IT 32.5 Unconstrained dialogue translation cepin Apr 2026 Official leaderboard
2 NileChat-3B-Base 30.4 Constrained dialogue translation, Thakaa Thakaa Official leaderboard
3 FCDS + Gemma 3 4B 26.5 Constrained dialogue translation FCDS Mar 2025 Official leaderboard
#ModelScoreSettingSubmitted byDateSource

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Multilingual

All 545 in Multilingual
  • MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
  • WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET. K-EXAONE 90.5%
  • MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language. Qwen3.7-Max 87%
  • CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories. Solar Open 2 90.7%
  • Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
  • MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%

Data audit

All 7 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
  • Pass Independent runs Scores from the official leaderboard (3 entries).
  • Note Models scored 3 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on alexandriax.dlnlp.ai: 2 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check