Benchmarks/Lech Mazur Writing

Lech Mazur Writing

Lech Mazur Writing — evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.

knowledge

Models Tested

87.3

Top Score

77.4

Average Score

Rankings

#	Model	Score
1	M Kimi K2 0905moonshotai	87.3
2	GPT-5 ChatOpenAI	87.2
3	GPT-5OpenAI	87.2
4	Qwen3 MaxAlibaba Qwen	87.1
5	M Kimi K2 0711moonshotai	86.9
6	o3 ProOpenAI	86.3
7	Gemini 2.5 ProGoogle DeepMind	86.0
8	Claude Opus 4.1Anthropic	85.4
9	DeepSeek V3.1DeepSeek	85.2
10	Qwen3 235B A22B Thinking 2507Alibaba Qwen	85.0
11	o3OpenAI	83.9
12	Qwen3 235B A22BAlibaba Qwen	83.0
13	DeepSeek-R1DeepSeek	83.0
14	GPT-4o (2024-11-20)OpenAI	81.8
15	Grok 4 FastxAI	81.1
16	Claude 3.7 SonnetAnthropic	81.1
17	Claude 3.7 Sonnet (thinking)Anthropic	81.1
18	Grok 4xAI	80.7
19	Gemma 3 4B (free)Google DeepMind	79.9
20	Gemma 3 4BGoogle DeepMind	79.9
21	Gemma 3 12B (free)Google DeepMind	79.9
22	Gemma 3 12BGoogle DeepMind	79.9
23	Gemma 3 27B (free)Google DeepMind	79.9
24	Gemma 3 27BGoogle DeepMind	79.9
25	ZA GLM 4.5z-ai	78.0
26	gpt-oss-120b (free)OpenAI	77.3
27	gpt-oss-120bOpenAI	77.3
28	gpt-oss-20b (free)OpenAI	77.3
29	gpt-oss-20bOpenAI	77.3
30	Gemini 2.5 FlashGoogle DeepMind	76.5
31	Grok 3xAI	76.4
32	Grok 3 BetaxAI	76.4
33	GPT-4.5OpenAI	75.6
34	o4 MiniOpenAI	75.0
35	Gemini 2.0 Flash Thinking (Jan 2025)Google	73.8
36	Grok 3 MinixAI	73.5
37	Grok 3 Mini BetaxAI	73.5
38	Claude 3.5 HaikuAnthropic	73.5
39	Qwen2.5-MaxAlibaba	72.9
40	Gemini 2.0 FlashGoogle DeepMind	71.5
41	o1OpenAI	70.2
42	Mistral Large 2407Mistral AI	69.0
43	GPT-4o-mini (2024-07-18)OpenAI	67.2
44	GPT-4o-miniOpenAI	67.2
45	o1-miniOpenAI	64.9
46	Llama 4 MaverickMeta	63.7
47	Grok-2 (Dec 2024)xAI	63.6
48	Phi 4Microsoft	62.6
49	o3 MiniOpenAI	61.7