# WritingBench

> WritingBench evaluates generative writing across six domains. This dated benchmark-owner table contains 54 source model rows, with overall and domain scores on the native 0-100 scale.

Canonical page: https://benchlm.ai/benchmarks/writingbench

- Category: [Instruction Following](/instruction-following)
- Last updated: November 27, 2025 source update

Evaluation results published by [WritingBench / X-PLUG project](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1). Published overall and six domain aggregates on a 0-100 point scale. The 1,000-query count applies to each overall row; domain counts are not reported.

WritingBench: A Comprehensive Benchmark for Generative Writing, WritingBench / X-PLUG project; official aggregate workbook. [Apache-2.0 license](/licenses/writingbench-apache-2.0.txt) · [Source and transformation notice](/licenses/writingbench-notice.txt). Aggregate worksheet values extracted to JSON; overall and six domain scores retained without rescaling. Three reviewed model profile references added. Published aggregate workbook only. No task texts, evaluation prompts, model responses, or model weights are included.

We extracted all 54 model rows from the official aggregate workbook at the pinned November 27, 2025 source update. This historical table names Claude Sonnet 4.5 as the judge. Its update date is separate from individual evaluation dates, which are not reported.

Overall and domain values retain their native 0-100 scale. They are judge scores, not accuracy percentages. The source already multiplied its original 10-point assessments by ten; we do not repeat that scaling or recompute the published overall score from domain averages.

Three profile references match reviewed model versions and modes. The other 51 source rows keep their own identities. Generation settings, thinking budgets, endpoints, and weight revisions remain unknown, including for the three linked models. These results are excluded from overall and category rankings.

- [Official aggregate workbook](https://huggingface.co/spaces/WritingBench/WritingBench/resolve/c06986e05aea53d625837e67c88944a2234271f1/score.xlsx)
- [Source license declaration](https://huggingface.co/spaces/WritingBench/WritingBench/blob/c06986e05aea53d625837e67c88944a2234271f1/README.md)
- [Apache 2.0 license copy](/licenses/writingbench-apache-2.0.txt)
- [Source and transformation notice](/licenses/writingbench-notice.txt)

## About WritingBench

- Year: 2025
- Tasks: 1,000 queries
- Format: Judge score, 0-100 points
- Paper: [WritingBench: A Comprehensive Benchmark for Generative Writing](https://arxiv.org/abs/2503.05244)

The source update is dated November 27, 2025 and names Claude Sonnet 4.5 as the judge. Individual run dates, generation parameters, thinking budgets, and domain counts are not reported in the workbook. This historical cohort stays display only and does not enter overall or category rankings.

WritingBench is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (54 source model rows)

| Source model | Overall | Academic & Engineering | Finance & Business | Politics & Law | Literature & Arts | Education | Advertising & Marketing |
|---|---|---|---|---|---|---|---|
| [gpt-5-2025-08-07](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 83.87 | 84.46 | 83.78 | 82.21 | 85.26 | 85.64 | 82.34 |
| [qwen3-235b-a22b-thinking-2507](/models/qwen3-235b-2507-reasoning) | 82.34 | 83.43 | 83.44 | 79.67 | 82.68 | 84.52 | 80.94 |
| [kimi-k2-instruct](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 81.26 | 82.23 | 81.90 | 80.32 | 81.73 | 80.97 | 80.02 |
| [claude-sonnet-4-5-20250929](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 80.71 | 80.77 | 80.54 | 79.59 | 81.26 | 82.32 | 80.45 |
| [o3-2025-04-16](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 80.46 | 80.83 | 81.15 | 78.31 | 80.47 | 81.59 | 81.23 |
| [qwen3-235b-a22b-instruct-2507](/models/qwen3-235b-2507) | 80.26 | 80.80 | 81.14 | 79.14 | 80.47 | 80.97 | 78.97 |
| [qwen3-max](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 80.26 | 80.46 | 80.10 | 78.70 | 81.50 | 81.75 | 79.70 |
| [claude-opus-4-5-20251101](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 79.78 | 79.31 | 80.00 | 78.05 | 81.41 | 81.30 | 79.11 |
| [doubao-seed-1-6-thinking-250715](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 79.29 | 80.79 | 79.74 | 78.05 | 78.37 | 81.48 | 77.95 |
| [gemini-2.5-pro](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 79.26 | 79.59 | 78.24 | 78.69 | 80.92 | 81.30 | 77.27 |
| [nanbeige4-3b-thinking-2511](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 79.03 | 80.77 | 82.37 | 77.41 | 76.05 | 80.81 | 76.55 |
| [deepseek-r1-0528](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 78.92 | 78.79 | 78.38 | 77.27 | 80.91 | 80.41 | 78.44 |
| [doubao-seed-1-6-thinking-250615](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 78.76 | 80.07 | 79.99 | 76.98 | 77.06 | 81.73 | 77.72 |
| [gemini-3-pro-preview](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 78.50 | 77.13 | 77.26 | 77.55 | 81.11 | 80.58 | 78.27 |
| [doubao-seed-1-6-250615](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 78.33 | 80.18 | 78.80 | 72.90 | 79.91 | 81.06 | 79.02 |
| [claude-haiku-4-5-20251001](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 77.09 | 77.54 | 78.61 | 75.33 | 76.35 | 79.62 | 75.59 |
| [claude-opus-4-1-20250805](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 76.36 | 76.89 | 75.56 | 74.19 | 78.05 | 77.33 | 77.16 |
| [claude-opus-4-20250514-thinking](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 75.12 | 75.60 | 74.57 | 73.09 | 77.20 | 75.78 | 74.98 |
| [qwen3-235b-a22b-thinking](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 74.73 | 75.45 | 74.84 | 73.30 | 74.67 | 76.41 | 74.50 |
| [grok-4-0709](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 74.65 | 75.44 | 73.99 | 73.08 | 74.66 | 77.48 | 74.73 |
| [claude-opus-4-20250514](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 74.45 | 73.90 | 73.96 | 73.05 | 76.31 | 75.23 | 74.81 |
| [claude-sonnet-4-20250514](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 74.10 | 75.35 | 74.13 | 71.55 | 74.66 | 74.99 | 74.84 |
| [claude-sonnet-4-20250514-thinking](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 74.07 | 75.08 | 74.52 | 70.71 | 75.26 | 76.04 | 73.88 |
| [claude-3-7-sonnet-20250219-thinking](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 73.40 | 73.11 | 73.12 | 72.43 | 73.93 | 74.43 | 74.11 |
| [chatgpt-4o-latest](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 73.22 | 72.79 | 73.08 | 72.16 | 73.58 | 73.71 | 74.77 |
| [o4-mini-2025-04-16](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 72.90 | 76.04 | 73.19 | 71.26 | 69.87 | 75.91 | 72.66 |
| [claude-3-7-sonnet-20250219](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 72.45 | 72.46 | 72.78 | 70.80 | 71.69 | 74.74 | 73.56 |
| [qwen3-235b-a22b-nothinking](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 72.44 | 72.40 | 72.78 | 71.36 | 72.67 | 74.25 | 71.70 |
| [qwq-32b](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 72.40 | 72.92 | 72.04 | 71.71 | 70.45 | 75.33 | 73.66 |
| [deepseek-r1](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 72.13 | 71.95 | 70.35 | 71.52 | 71.93 | 74.54 | 74.45 |
| [grok-3](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 71.72 | 71.40 | 71.73 | 72.19 | 71.14 | 74.68 | 69.63 |
| [gpt-4.1-2025-04-14](/models/gpt-4-1) | 70.90 | 71.52 | 70.26 | 70.21 | 70.45 | 72.20 | 71.77 |
| [deepseek-v3-250324](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 69.36 | 68.97 | 68.13 | 68.27 | 69.78 | 71.21 | 71.41 |
| [o3-mini](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 68.02 | 69.52 | 68.61 | 66.92 | 66.54 | 71.48 | 65.95 |
| [gpt-4.5-preview](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 67.61 | 68.22 | 66.17 | 66.83 | 66.40 | 70.56 | 69.59 |
| [gemini-2.0-flash](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 66.80 | 67.51 | 65.78 | 65.84 | 66.24 | 69.53 | 67.50 |
| [qwen-max](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 66.78 | 66.37 | 65.52 | 65.22 | 67.36 | 69.77 | 68.44 |
| [o1-preview-2024-09-12](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 63.44 | 63.56 | 62.30 | 62.37 | 63.18 | 65.53 | 65.39 |
| [deepseek-v3](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 59.23 | 59.64 | 57.86 | 58.32 | 57.85 | 62.34 | 61.67 |
| [gemini-1.5-pro](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 58.80 | 58.83 | 55.69 | 57.22 | 60.33 | 61.78 | 61.61 |
| [qwen-2.5-72b-instruct](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 57.78 | 59.37 | 56.93 | 57.27 | 55.33 | 62.25 | 57.53 |
| [gpt-4o-mini](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 56.40 | 57.14 | 54.69 | 54.34 | 56.49 | 59.05 | 59.03 |
| [mistral-large-instruct-2411](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 54.44 | 55.54 | 54.35 | 53.73 | 51.67 | 57.30 | 55.77 |
| [claude-3-5-sonnet-20241022](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 53.76 | 52.77 | 52.44 | 51.69 | 53.10 | 55.78 | 59.69 |
| [llama-4-maverick-17b-128e](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 52.55 | 51.83 | 51.58 | 51.35 | 51.25 | 55.42 | 56.36 |
| [llama-4-scout-17b-16e-instruct](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 52.02 | 52.57 | 52.05 | 51.47 | 49.19 | 54.76 | 53.78 |
| [qwen-2.5-7b-instruct](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 49.46 | 51.86 | 50.43 | 49.21 | 43.79 | 53.59 | 49.64 |
| [claude-3-5-haiku-20241022](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 49.06 | 49.70 | 48.72 | 47.33 | 46.25 | 50.20 | 54.52 |
| [llama-3.3-70b-instruct](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 48.04 | 47.58 | 48.52 | 45.73 | 46.04 | 50.86 | 51.84 |
| [qwen3-0.6b-thinking](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 45.08 | 50.13 | 47.28 | 45.65 | 37.98 | 47.46 | 42.06 |
| [qwen3-0.6b-nothinking](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 41.47 | 46.37 | 43.52 | 41.85 | 34.61 | 42.81 | 39.72 |
| [llama-3.1-8b-instruct](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 40.18 | 41.58 | 41.49 | 37.02 | 36.52 | 42.92 | 44.02 |
| [llama-3.2-3b-instruct](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 38.14 | 40.26 | 39.89 | 34.78 | 34.27 | 41.01 | 40.84 |
| [llama-3.2-1b-instruct](https://huggingface.co/spaces/WritingBench/WritingBench/tree/c06986e05aea53d625837e67c88944a2234271f1) | 28.74 | 32.56 | 30.03 | 25.44 | 25.18 | 30.11 | 30.73 |

All seven columns use native 0-100 score points, displayed to two decimals. The 1,000-query total is not each domain's denominator. Generation settings and individual run dates are not reported.

## FAQ

### What does WritingBench measure?

WritingBench evaluates generative writing across six domains. This dated benchmark-owner table contains 54 source model rows, with overall and domain scores on the native 0-100 scale.

### Which model leads the published WritingBench snapshot?

gpt-5-2025-08-07 currently leads the published WritingBench snapshot with a score of 83.87.

### How many models are evaluated on WritingBench?

The November 27, 2025 source update contains 54 source model rows.

### Does WritingBench affect BenchLM's overall score?

Not directly. WritingBench is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.