Benchmark Almanac

MultiGEC 2025

Not in model cards

Models correct whole texts in 12 European languages. One track rewards minimal edits, and the other rewards fluent rewrites.

Four teams submitted systems. UAM-CSI used Gemma 2, and Lattice used Llama. The organizers publish separate rankings for each track.

Released
June 2024
Kind
Reading in many languages
Level
School
Scored
Checked automatically
Answers
Open-ended
Tasks
Public, plus a private test set
Measures
Capability
Language
Many languages
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
In views
Many languages
Strongest model tested
Gemma 2 9B #202 on the capability index
Last model added
July 2024
Scores refreshed
November 20th, 2026
3
Entries on its own leaderboard, 2 models we track

Gemma 2 9B leads with 56.8 Gemma 2 9B leads with 56.8

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

  1. 1 Gemma 2 9B 56.8
  2. 2 Llama 3.1-8B 35.6
  3. 3 LLaMA 3 + XLM-RoBERTa 35.1

Source: Official MultiGEC 2025 leaderboard

Source: Official MultiGEC 2025 leaderboard

#EntryScoreSettingSubmitted byDateSource
1 Gemma 2 9B 56.8 UAM-CSI Jun 2024 Official leaderboard
2 Llama 3.1-8B 35.6 Organizers Jul 2024 Official leaderboard
3 LLaMA 3 + XLM-RoBERTa 35.1 Lattice Official leaderboard
#ModelScoreSettingSubmitted byDateSource
1 Gemma 2 9B 56.8 UAM-CSI Jun 2024 Official leaderboard
2 Llama 3.1-8B 35.6 Organizers Jul 2024 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard
35.0 40.0 45.0 50.0 55.0 60.0 2024 35.0 40.0 45.0 50.0 55.0 60.0 2024

Source: Official MultiGEC 2025 leaderboard

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

7 of 8 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in July 2024, for Llama 3.1-8B. 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 warning 1 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (3 entries).
  • Note Models scored Only 2 models we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in July 2024, for Llama 3.1-8B.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemma 2 9B (#202).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on spraakbanken.github.io: 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