Lech Mazur Creative Writing leaderboard
As of 5 Nov 2026, the top score on Lech Mazur Creative Writing is 86.0% by GPT-5 (OpenAI), ahead of Kimi K2 at 85.6%, across 42 model configurations with a published result (Lech Mazur, result dated 7 Aug 2025). Models write short stories to constraints and a panel of judge models scores them on craft criteria. Lech Mazur Creative Writing is shown for reference only and does not count toward the BenchLeader Index.
Key facts (as of 5 Nov 2026)
- GPT-5 holds the top Lech Mazur Creative Writing score at 86.0% (Lech Mazur, 7 Aug 2025).
- Kimi K2 is second on Lech Mazur Creative Writing at 85.6% (Lech Mazur, 12 Jul 2025).
- Lech Mazur Creative Writing: Short-story writing judged by a panel of models (Lech Mazur).
- 42 model configurations have a published Lech Mazur Creative Writing result on BenchLeader (BenchLeader, 5 Nov 2026).
- Lech Mazur Creative Writing does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).
Short-story writing judged by a panel of models.
- Published by
- Lech Mazurdata via Epoch AI Benchmarking Hub
- Category
- Human preference
- Index weight
- Reference only
- Models
- 42
- Data as of
- 5 Nov 2026
CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.
What the test looks like
Models write short stories to constraints and a panel of judge models scores them on craft criteria.
How it is scored
Mean judge score, rescaled to percent.
What to keep in mind
Judged by models, so it reflects their taste; widely followed for creative writing.
- 1GPT-5 (medium)86.0%
- 2Kimi K285.6%
- 3Claude Opus 4.184.7%
- 4o3-pro (medium)84.4%
- 5o3 (medium)83.9%
- 6Gemini 2.5 Pro83.8%
- 7Claude Opus 483.6%
- 8GPT-5 mini (medium)83.1%
- 9Qwen3 235B A22B83.0%
- 10DeepSeek R183.0%
- 11Qwen3 235B A22B 2507 (thinking)82.4%
- 12DeepSeek R1 052881.9%
- 13GPT-4o81.8%
- 14Claude Sonnet 481.4%
- 15Claude 3.7 Sonnet81.1%
| # | ||||
|---|---|---|---|---|
| 1 |  GPT-5medium | 86.0% | 58.1 | 2025-08-07 |
| 2 |  Kimi K2open ↗ | 85.6% | 51.0 | 2025-07-12 |
| 3 |  Claude Opus 4.1 | 84.7% | 51.4 | 2025-08-05 |
| 4 | o3-promedium | 84.4% | – | 2025-06-10 |
| 5 | o3medium | 83.9% | 53.3 | 2025-04-16 |
| 6 |  Gemini 2.5 Pro | 83.8% | 54.5 | 2025-06-17 |
| 7 | Claude Opus 4 | 83.6% | 52.6 | 2025-05-22 |
| 8 | GPT-5 minimedium | 83.1% | 53.5 | 2025-08-07 |
| 9 |  Qwen3 235B A22Bopen ↗ | 83.0% | 50.0 | 2025-04-29 |
| 10 |  DeepSeek R1open ↗ | 83.0% | 47.3 | 2025-01-20 |
| 11 | Qwen3 235B A22B 2507thinkingopen ↗ | 82.4% | 51.9 | 2025-07-25 |
| 12 | DeepSeek R1 0528open ↗ | 81.9% | 49.3 | 2025-05-28 |
| 13 | GPT-4o | 81.8% | 43.3 | 2024-11-20 |
| 14 | Claude Sonnet 4 | 81.4% | 50.5 | 2025-05-22 |
| 15 | Claude 3.7 Sonnet | 81.1% | 49.9 | 2025-02-24 |
| 16 | Claude 3.5 Sonnet | 80.3% | 47.1 | 2024-10-22 |
| 17 | QwQ-32Bthinkingopen ↗ | 80.2% | – | 2025-03-05 |
| 18 | Gemma 3 27Bopen ↗ | 79.9% | 39.9 | 2025-03-12 |
| 19 |  Mistral Medium 3 | 77.3% | 44.3 | 2025-05-07 |
| 20 | gpt-oss-120bopen ↗ | 77.1% | 45.5 | 2025-08-05 |
| 21 |  Grok 4 | 76.9% | 58.3 | 2025-07-09 |
| 22 | Gemini 2.5 Flashthinking | 76.5% | 48.3 | 2025-04-17 |
| 23 | Grok 3 | 76.4% | 52.5 | 2025-04-09 |
| 24 | GPT-4.5 | 75.6% | 50.8 | 2025-02-27 |
| 25 | Qwen3 30B A3Bopen ↗ | 75.3% | 48.2 | 2025-04-29 |
| 26 | o4-minimedium | 75.0% | 51.8 | 2025-04-16 |
| 27 | Gemini 2.0 Flash Thinkingthinking | 73.8% | 45.3 | 2025-01-21 |
| 28 | Grok 3 minilow | 73.5% | 49.7 | 2025-04-09 |
| 29 | Claude 3.5 Haiku | 73.5% | 38.8 | 2024-10-22 |
| 30 |  GLM-4.5open ↗ | 73.4% | 51.6 | 2025-08-03 |
| 31 | Qwen2.5-Maxmax | 72.9% | – | 2025-01-28 |
| 32 | Gemini 2.0 Flash | 71.5% | 43.5 | 2024-12-11 |
| 33 | o1medium | 70.2% | 48.1 | 2024-12-17 |
| 34 | Mistral Large 2open | 69.0% | 40.9 | 2024-07-24 |
| 35 | GPT-4o mini | 67.2% | 35.4 | 2024-07-18 |
| 36 | o1-minimedium | 64.9% | 44.4 | 2024-09-12 |
| 37 | Grok 2open | 63.6% | 42.3 | 2024-12-12 |
| 38 |  Phi-4open ↗ | 62.6% | 39.4 | 2024-12-12 |
| 39 |  Llama 4 Maverickopen ↗ | 62.0% | 42.1 | 2025-04-05 |
| 40 | o3-minihigh | 61.7% | 47.7 | 2025-01-31 |
| 41 | o3-minimedium | 61.5% | 45.2 | 2025-01-31 |
| 42 |  Nova Pro | 60.5% | 40.9 | 2024-12-03 |
More human preference benchmarks · All LLM benchmarks
Cite as: BenchLeader, “Lech Mazur Creative Writing leaderboard”, data as of 5 Nov 2026, https://www.benchleader.com/benchmarks/lech_mazur_writing.
Lech Mazur Creative Writing: questions
- What does Lech Mazur Creative Writing measure?
- Models write short stories to constraints and a panel of judge models scores them on craft criteria. Scores are reported in percent of tasks solved; higher is better.
- What is the top score on Lech Mazur Creative Writing?
- As of 5 Nov 2026, the highest score on Lech Mazur Creative Writing is 86.0% by GPT-5 (result dated 7 Aug 2025), ahead of Kimi K2 at 85.6%. Scores come from Lech Mazur and are re-read daily.
- Which AI model leads Lech Mazur Creative Writing?
- GPT-5 leads Lech Mazur Creative Writing with 86.0% as of 5 Nov 2026 (result dated 7 Aug 2025), ahead of Kimi K2 at 85.6%.
- How many models have Lech Mazur Creative Writing results?
- 42 model configurations have a Lech Mazur Creative Writing result on BenchLeader, all taken from Lech Mazur via Epoch AI Benchmarking Hub.
- Who runs Lech Mazur Creative Writing and how often is it updated?
- Lech Mazur Creative Writing is published by Lech Mazur. BenchLeader re-reads the published results once a day and records the date each result was published.
- Does Lech Mazur Creative Writing count toward the BenchLeader Index?
- No. Lech Mazur Creative Writing is shown for reference but left out of the composite index.