Benchmark Almanac

Grammarly Corpus of Discourse Coherence

PARSEQ 55.7% tops its leaderboard
Not in model cards

Models rate the coherence of emails, reviews, and answers to online questions. Each of four collections has 200 test texts with expert ratings.

An independent team reported classification accuracy on each collection. Another study tested language models on a selection that excluded Yahoo Answers. Grammarly requires approval for access.

Released
July 2018
Kind
Reading comprehension
Level
School
Scored
Checked automatically
Answers
Multiple choice
Tasks
Kept private
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
11
Entries in its paper, 0 models we track

PARSEQ tops the leaderboard with 55.7%

Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. The paper reports no whole-corpus score, so this is the plain mean of the four domain accuracies. 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.

  1. 1 PARSEQ 55.7%
  2. 2 SENTAVG 54.6%
  3. 3 CLIQUE 54.5%
  4. 4 Baseline 51.8%
  5. 5 EGRID CONV +coref 51.6%
  6. 6 EGRID CONV 50.6%
  7. 7 EGRAPH +coref 48.9%
  8. 8 EGRAPH 48.1%
  9. 9 EGRID +coref 46.4%
  10. 10 LEXGRAPH 45.3%
  11. 11 EGRID 43.1%

Source: The Grammarly Corpus of Discourse Coherence paper

#EntryScoreSettingDateSource
1 PARSEQ 55.7% Official leaderboard
2 SENTAVG 54.6% Official leaderboard
3 CLIQUE 54.5% Official leaderboard
4 Baseline 51.8% Official leaderboard
5 EGRID CONV +coref 51.6% Official leaderboard
6 EGRID CONV 50.6% Official leaderboard
7 EGRAPH +coref 48.9% Official leaderboard
8 EGRAPH 48.1% Official leaderboard
9 EGRID +coref 46.4% Official leaderboard
10 LEXGRAPH 45.3% Official leaderboard
11 EGRID 43.1% Official 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 Knowledge

All 332 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy. Seed1.8 92.3%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (11 entries).
  • Pass Models scored 11 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on aclanthology.org: 11 entries at the last read, none a model we track.
  • Pass Last read November 21st, 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