GLUE
Models predict labels or similarity scores across nine English language-understanding tasks. The overall score averages task scores. Tasks with several metrics first average those metrics.
The separate diagnostic set does not determine the aggregate score. Some component tasks already have almanac records. SuperGLUE is a separate successor suite with different tasks.
- Released
- April 2018
- Kind
- Language reasoning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
In the authors’ words
For natural language understanding (NLU) technology to be maximally useful, both practically and as a scientific object of study, it must be general: it must be able to process language in a way that is not exclusively tailored to any one specific task or dataset. In pursuit of this objective, we introduce the General Language Understanding Evaluation benchmark (GLUE), a tool for evaluating and analyzing the performance of models across a diverse range of existing NLU tasks. GLUE is model-agnostic, but it incentivizes sharing knowledge across tasks because certain tasks have very limited training data. We further provide a hand-crafted diagnostic test suite that enables detailed linguistic analysis of NLU models. We evaluate baselines based on current methods for multi-task and transfer learning and find that they do not immediately give substantial improvements over the aggregate performance of training a separate model per task, indicating room for improvement in developing general and robust NLU systems.
BiLSTM +Attn, ELMo tops the leaderboard with 70.0
Best score per entry from the benchmark's paper, read on November 19th, 2026. A paper’s table doesn’t add newer models. 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 BiLSTM +Attn, ELMo Multi-Task Training 70.0
- 2 BiLSTM +ELMo Multi-Task Training 67.7
- 3 GenSen Pre-Trained Sentence Representation Models 66.2
- 4 BiLSTM +Attn Multi-Task Training 65.6
- 5 BiLSTM Multi-Task Training 64.2
- 6 BiLSTM +CoVe Single-Task Training 64.0
- 7 InferSent Pre-Trained Sentence Representation Models 63.9
- 8 BiLSTM +Attn, CoVe Single-Task Training 63.2
- 9 DisSent Pre-Trained Sentence Representation Models 62.0
- 10 Skip-Thought Pre-Trained Sentence Representation Models 61.3
- 11 CBoW Pre-Trained Sentence Representation Models 58.9
Source: The GLUE paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | BiLSTM +Attn, ELMo | 70.0 | Multi-Task Training | Official leaderboard | |
| 2 | BiLSTM +ELMo | 67.7 | Multi-Task Training | Official leaderboard | |
| 3 | GenSen | 66.2 | Pre-Trained Sentence Representation Models | Official leaderboard | |
| 4 | BiLSTM +Attn | 65.6 | Multi-Task Training | Official leaderboard | |
| 5 | BiLSTM | 64.2 | Multi-Task Training | Official leaderboard | |
| 6 | BiLSTM +CoVe | 64.0 | Single-Task Training | Official leaderboard | |
| 7 | InferSent | 63.9 | Pre-Trained Sentence Representation Models | Official leaderboard | |
| 8 | BiLSTM +Attn, CoVe | 63.2 | Single-Task Training | Official leaderboard | |
| 9 | DisSent | 62.0 | Pre-Trained Sentence Representation Models | Official leaderboard | |
| 10 | Skip-Thought | 61.3 | Pre-Trained Sentence Representation Models | Official leaderboard | |
| 11 | CBoW | 58.9 | Pre-Trained Sentence Representation Models | 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
- 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 Public tasks, plus a private test set.
- 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 Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 11 entries at the last read, none a model we track.
- Pass Last read November 19th, 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.