legal benchmark
WritingBench
A comprehensive benchmark for evaluating large language models' generative writing capabilities across 6 core writing domains (Academic & Engineering, Finance & Business, Politics & Law, Literature & Art, Education, Advertising & Marketing) and 100 subdomains. Contains 1,239 queries with a query-dependent evaluation framework that dynamically generates 5 instance-specific assessment criteria for each writing task, using a fine-tuned critic model to score responses on style, format, and length dimensions.
Updated Aug 7, 2026
Published models15
Registry coverage15
MetricScore
EvidenceB
WritingBench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 88.3% | 100.0% | 15 | C | |
| 2 | AC | 87.3% | 92.9% | 15 | C | |
| 3 | AC | 86.7% | 85.7% | 15 | C | |
| 4 | AC | 86.2% | 78.6% | 15 | C | |
| 5 | AC | 85.5% | 71.4% | 15 | C | |
| 6 | AC | 85.5% | 64.3% | 15 | C | |
| 7 | AC | 85.2% | 57.1% | 15 | C | |
| 8 | AC | 85.2% | 50.0% | 15 | C | |
| 9 | AC | 84.6% | 42.9% | 15 | C | |
| 10 | AC | 84.0% | 35.7% | 15 | C | |
| 11 | AC | 83.1% | 28.6% | 15 | C | |
| 12 | AC | 82.9% | 21.4% | 15 | C | |
| 13 | AC | 82.6% | 14.3% | 15 | C | |
| 14 | AC | 82.5% | 7.1% | 15 | C | |
| 15 | MA | 73.8% | 0.0% | 15 | C |
Score distribution
Top published rows on the benchmark's original scale.
WritingBench highlights
The top published results on this benchmark's own scale.
What is WritingBench?
Definition and scoring fields from the benchmark registry.
A comprehensive benchmark for evaluating large language models' generative writing capabilities across 6 core writing domains (Academic & Engineering, Finance & Business, Politics & Law, Literature & Art, Education, Advertising & Marketing) and 100 subdomains. Contains 1,239 queries with a query-dependent evaluation framework that dynamically generates 5 instance-specific assessment criteria for each writing task, using a fine-tuned critic model to score responses on style, format, and length dimensions.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- WritingBench
- Modality
- text
- Primary category
- legal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- writingbench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about WritingBench.
Which model scores highest on WritingBench?
Qwen3-235B-A22B-Thinking-2507 is currently ranked first with 88.3%.
What does WritingBench measure?
A comprehensive benchmark for evaluating large language models' generative writing capabilities across 6 core writing domains (Academic & Engineering, Finance & Business, Politics & Law, Literature & Art, Education, Advertising & Marketing) and 100 subdomains. Contains 1,239 queries with a query-dependent evaluation framework that dynamically generates 5 instance-specific assessment criteria for each writing task, using a fine-tuned critic model to score responses on style, format, and length dimensions.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
15 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is marked as eligible for the current LLMBoard capability methodology.