EQ-Bench Creative Writing v3

Short creative writing pieces from fixed prompts, compared pairwise by a judge model and rated on an Elo scale.

CategoryGeneral
MetricJudge Elo
SourceEQ-Bench (original)
LicenseNone stated
Benchmark pageeqbench.com
StatusScored
Weight0.7 within General
FitDiscrimination 1.59, noise 0.35

Results

#ModelProviderResultDate
1 GPT-6 Astra OpenAI 2,177 2026-11-11
2 Kimi K3.1 Pro Moonshot AI 2,173 2026-11-11
3 Claude Fable 5.1 Anthropic 2,155 2026-11-11
4 Claude Opus 5 Anthropic 2,135 2026-11-11
5 GPT-6 Sol OpenAI 2,126 2026-11-11
6 Kimi K3 Moonshot AI 2,083 2026-11-11
7 GLM-5.3 Zhipu AI 2,076 2026-11-11
8 Claude Opus 5.5 Anthropic 2,051 2026-11-11
9 Grok 4.7 xAI 2,012 2026-11-11
10 Muse Wonder Meta 2,007 2026-11-11
11 GPT-5.6 Sol OpenAI 1,974 2026-11-11
12 Claude Fable 5 Anthropic 1,944 2026-11-11
13 Muse Spark 1.1 Meta 1,928 2026-11-11
14 Claude Opus 4.7 Anthropic 1,915 2026-11-11
15 Muse Spark 1.3 Meta 1,907 2026-11-11
16 GPT-5.6 Terra OpenAI 1,856 2026-11-11
17 GPT-5.5 OpenAI 1,845 2026-11-11
18 Qwen3.8 2.4T A95B Alibaba 1,844 2026-11-11
19 Muse Spark 1.2 Meta 1,842 2026-11-11
20 GPT-5.4 OpenAI 1,841 2026-11-11
21 Claude Opus 4.8 Anthropic 1,840 2026-11-11
22 GPT-5.6 Luna OpenAI 1,832 2026-11-11
23 Claude Sonnet 4.6 Anthropic 1,811 2026-11-11
24 Claude Opus 4.6 Anthropic 1,810 2026-11-11
25 Muse Glimmer 30B Meta 1,804 2026-11-11
26 Claude Sonnet 5 Anthropic 1,798 2026-11-11
27 GLM-5.2 Zhipu AI 1,759 2026-11-11
28 Gemini 4 Argon Google 1,758 2026-11-11
29 Gemini 3.8 Flash Google 1,744 2026-11-11
30 Kimi K2.6 Moonshot AI 1,721 2026-11-11
31 Gemini 3.7 Flash Google 1,720 2026-11-11
32 GPT-5.2 OpenAI 1,703 2026-11-11
33 GPT-5.3 Chat (latest) OpenAI 1,690 2026-11-11
34 Claude Opus 4.5 Anthropic 1,686 2026-11-11
35 Claude Sonnet 4.5 Anthropic 1,677 2026-11-11
36 o3 OpenAI 1,675 2026-11-11
37 Qwen3.8 27B Alibaba 1,671 2026-11-11
38 Kimi K2 Instruct Moonshot AI 1,666 2026-11-11
39 GPT-5.4 mini OpenAI 1,665 2026-11-11
40 Kimi K2 Thinking Moonshot AI 1,631 2026-11-11
41 GPT-5 OpenAI 1,626 2026-11-11
42 Inkling Thinking Machines 1,609 2026-11-11
43 Gemini 3.6 Flash Google 1,602 2026-11-11
44 GLM-5 Zhipu AI 1,601 2026-11-11
45 GLM-5.1 Zhipu AI 1,594 2026-11-11
46 Kimi K2.5 Moonshot AI 1,579 2026-11-11
47 Claude Opus 4 Anthropic 1,578 2026-11-11
48 Grok 4.5 xAI 1,576 2026-11-11
49 DeepSeek V4 Flash DeepSeek 1,559 2026-11-11
50 Gemini 3.5 Flash Lite Google 1,559 2026-11-11
51 DeepSeek V4 Pro DeepSeek 1,553 2026-11-11
52 DeepSeek V4.1 Flash DeepSeek 1,540 2026-11-11
53 Gemini 3 Pro Preview Google 1,524 2026-11-11
54 DeepSeek V3.2 DeepSeek 1,515 2026-11-11
55 DeepSeek-R1 DeepSeek 1,500 2026-11-11
56 MiMo-V2.5-Pro Xiaomi 1,493 2026-11-11
57 Inkling Small Thinking Machines 1,491 2026-11-11
58 Gemini 3.1 Pro Preview Google 1,491 2026-11-11
59 Claude Sonnet 4 Anthropic 1,483 2026-11-11
60 Qwen3.5 397B-A17B Alibaba 1,478 2026-11-11
61 Mistral Medium 3.1 Mistral 1,476 2026-11-11
62 DeepSeek V3 0324 DeepSeek 1,472 2026-11-11
63 Claude Sonnet 3.5 v2 Anthropic 1,451 2026-11-11
64 DeepSeek V4 Flash 0731 DeepSeek 1,441 2026-11-11
65 DeepSeek V3.1 DeepSeek 1,436 2026-11-11
66 Gemini 2.5 Pro Preview 06-05 Google 1,422 2026-11-11
67 DeepSeek R1 0528 DeepSeek 1,422 2026-11-11
68 Hermes 4 405B Nousresearch 1,421 2026-11-11
69 GPT-4.1 OpenAI 1,420 2026-11-11
70 GLM-4.7 Zhipu AI 1,414 2026-11-11
71 Claude Sonnet 3.7 Anthropic 1,412 2026-11-11
72 GLM-4.6 Zhipu AI 1,412 2026-11-11
73 Gemma 4 31B IT Google 1,369 2026-11-11
74 Qwen3 235B-A22B Thinking Alibaba 1,366 2026-11-11
75 MiniMax-M2.5 MiniMax 1,362 2026-11-11
76 GLM-4.5 Zhipu AI 1,344 2026-11-11
77 Grok 4.1 Fast xAI 1,328 2026-11-11
78 GPT-5 Mini OpenAI 1,314 2026-11-11
79 Gemma 4 26B A4B IT Google 1,305 2026-11-11
80 Gemma 4 12B IT Google 1,290 2026-11-11
81 DeepSeek-V3.2-Speciale DeepSeek 1,277 2026-11-11
82 Gemma 3 27B IT Google 1,266 2026-11-11
83 GPT-4.5 OpenAI 1,259 2026-11-11
84 QwQ 32B Alibaba 1,258 2026-11-11
85 Reka Flash 3 Reka 1,229 2026-11-11
86 Grok 3 xAI 1,186 2026-11-11
87 GPT-4.1 mini OpenAI 1,145 2026-11-11
88 Cohere Command A Cohere 1,145 2026-11-11
89 Claude Haiku 3.5 Anthropic 1,144 2026-11-11
90 GLM-4.7-Flash Zhipu AI 1,139 2026-11-11
91 Gemma 3 12B IT Google 1,131 2026-11-11
92 Gemini 2.0 Flash Google 1,131 2026-11-11
93 Gemma 4 E4B IT Google 1,093 2026-11-11
94 Gemma 3 4B IT Google 1,066 2026-11-11
95 Pixtral Large (latest) Mistral 986 2026-11-11
96 Mistral Large 2.1 Mistral 982 2026-11-11
97 GPT OSS 120B OpenAI 956 2026-11-11
98 GPT-4.1 nano OpenAI 939 2026-11-11
99 Mistral Nemo Mistral 878 2026-11-11
100 GPT-4o mini OpenAI 871 2026-11-11
101 Llama 3.1-405B Meta 868 2026-11-11
102 Llama 4 Maverick Meta 858 2026-11-11
103 Gemma 2 9B Google 840 2026-11-11
104 Llama-3.1-70B-Instruct Meta 782 2026-11-11
105 Llama 4 Scout Meta 781 2026-11-11
106 Mistral Small 3.1 24B Mistral 759 2026-11-11
107 GPT-4 OpenAI 750 2026-11-11
108 Claude Haiku 3 Anthropic 716 2026-11-11
109 Llama-3.1-8B-Instruct Meta 711 2026-11-11
110 Mistral Small 3 Mistral 705 2026-11-11
111 GPT-5 Nano OpenAI 703 2026-11-11
112 GPT OSS 20B OpenAI 665 2026-11-11
113 Llama 3.2 3B Instruct Meta 594 2026-11-11
114 GPT-3.5-turbo OpenAI 450 2026-11-11
115 Llama 3.2 1B Instruct Meta 200 2026-11-11