Clichés

Subcategory of Creative Writing. 155 models scored.

Model Leaderboard

All models ranked by their Clichés subcategory score.

# Model Clichés Creative Writing Overall
1 o4 Mini High 90.38% 82.72% 90.29%
2 Qwen3.6 Max Preview 89.87% 88.42% 94.54%
3 GPT-5 89.59% 86.87% 91.93%
4 Gemini 3.1 Pro (Preview) 88.95% 85.44% 94.37%
5 Grok 4.20 (Reasoning) 87.99% 86.25% 91.39%
6 Grok 4.3 (Reasoning) 87.57% 85.11% 93.60%
7 Qwen3.7 Max 87.36% 85.39% 95.75%
8 Grok 4.20 (Beta, Reasoning) 87.27% 84.50% 91.49%
9 Gemini 2.5 Pro 87.21% 81.03% 88.53%
10 o4 Mini 86.60% 82.04% 88.35%
11 GPT-5.4 (Reasoning) 86.52% 91.17% 93.24%
12 Grok 4.20 86.50% 83.44% 81.70%
13 GPT-5.1 86.39% 87.20% 92.54%
14 Qwen 3.6 35B 86.36% 85.97% 89.05%
15 Grok 4.3 85.60% 84.51% 78.66%
16 Qwen 3.6 Flash 85.50% 86.02% 90.65%
17 Grok 4.20 (Beta) 85.46% 82.80% 83.85%
18 GPT-5.4 (Reasoning, Low) 84.51% 90.51% 91.41%
19 Qwen 3.5 Plus (2026-04-20) 84.50% 85.18% 91.51%
20 GPT-5.4 84.30% 90.94% 84.32%
21 DeepSeek V3.1 83.91% 77.45% 82.39%
22 Z.AI GLM 4.6 83.84% 78.86% 89.11%
23 Gemma 3 27B 83.82% 78.79% 77.85%
24 GPT-4.1 83.80% 81.24% 88.68%
25 Claude Opus 4.7 (Reasoning) 83.59% 84.73% 93.23%
26 Claude Opus 4.8 (Reasoning) 83.58% 85.25% 92.22%
27 Skyfall 36B V2 83.52% 83.32% 65.76%
28 GPT-5.4 Mini (Reasoning) 83.22% 88.66% 90.65%
29 Qwen 3.5 397B A17B 83.12% 86.93% 91.73%
30 Claude Opus 4.8 (Reasoning, Low) 83.05% 85.86% 92.14%
31 Gemma 3 12B 82.85% 75.38% 78.41%
32 Rocinante 12B 82.68% 81.94% 54.54%
33 Hermes 3 405B 82.60% 80.92% 82.86%
34 Claude Opus 4.7 82.11% 84.74% 89.93%
35 Qwen 3.5 Flash 82.05% 83.81% 86.38%
36 Qwen3 235B A22B Instruct 2507 82.05% 84.81% 80.10%
37 ByteDance Seed 2.0 Mini 81.90% 80.11% 86.91%
38 Grok 4.1 Fast 81.78% 82.14% 89.55%
39 Gemini 3.5 Flash (Reasoning) 81.76% 79.87% 94.08%
40 Qwen 3 32B 81.72% 81.30% 82.21%
41 Z.AI GLM 4.7 81.62% 78.89% 88.69%
42 Aion 2.0 81.53% 80.24% 89.21%
43 GPT-5.5 81.40% 90.39% 89.09%
44 Mistral Large 2 81.36% 81.86% 82.41%
45 GPT-5.5 (Reasoning) 81.35% 90.26% 92.98%
46 DeepSeek V3.2 81.32% 79.95% 82.25%
47 Gemini 3 Flash (Preview, Reasoning) 81.18% 75.87% 90.50%
48 Qwen 3.5 35B 81.11% 83.51% 88.00%
49 Z.AI GLM 4.7 Flash 81.09% 77.36% 84.82%
50 Mistral Large 3 80.74% 81.21% 85.43%
51 GPT-4.1 Nano 80.71% 71.81% 71.94%
52 Qwen 3.6 27B 80.66% 82.81% 89.72%
53 Gemini 3 Pro (Preview) 80.50% 77.77% 88.79%
54 DeepSeek V3 (2025-03-24) 80.49% 82.34% 81.99%
55 GPT-4o, May 13th (temp=1) 80.44% 75.88% 83.80%
56 GPT-4.1 Mini 80.38% 74.52% 83.20%
57 Gemini 3.5 Flash (Reasoning, Minimal) 80.34% 78.55% 86.47%
58 Gemma 4 26B 80.33% 75.17% 85.84%
59 Gemini 3 Flash (Preview) 80.32% 75.04% 85.35%
60 Qwen 3.5 122B 80.31% 83.02% 91.53%
61 GPT-4o, Aug. 6th (temp=1) 80.25% 75.50% 82.62%
62 Gemma 3 4B 80.17% 72.10% 68.57%
63 DeepSeek V4 Flash (Reasoning) 80.09% 83.03% 89.01%
64 Mistral Large 80.04% 82.02% 80.15%
65 Gemini 3.1 Flash Lite 79.97% 76.01% 85.75%
66 Mistral Medium 3.1 79.96% 81.70% 77.83%
67 GPT-5.4 Mini 79.92% 88.10% 82.43%
68 Qwen 3.5 9B 79.82% 84.35% 86.05%
69 DeepSeek V3 (2024-12-26) 79.81% 77.88% 83.68%
70 Arcee AI: Trinity Mini 79.76% 74.01% 70.90%
71 Gemma 4 26B (Reasoning) 79.74% 76.38% 91.49%
72 Gemini 3.1 Flash Lite (Preview) 79.66% 75.78% 85.87%
73 Gemma 4 31B (Reasoning) 79.53% 78.13% 91.71%
74 DeepSeek V4 Flash 79.51% 83.42% 82.02%
75 Gemini 3.1 Flash Lite (Reasoning) 79.50% 76.31% 86.41%
76 WizardLM 2 8x22b 79.40% 79.06% 71.06%
77 Llama 3.1 8B 79.32% 76.54% 63.35%
78 DeepSeek-V2 Chat 79.10% 77.20% 84.83%
79 GPT-5.5 (Reasoning, Low) 78.89% 90.24% 92.59%
80 Z.AI GLM 5 78.86% 83.63% 91.23%
81 GPT-5.4 Mini (Reasoning, Low) 78.74% 87.72% 85.75%
82 Ministral 3 14B 78.70% 79.11% 72.54%
83 MiniMax M3 78.49% 84.57% 90.88%
84 GPT-5 Mini 78.48% 80.48% 92.62%
85 Qwen 3.5 27B 78.44% 82.54% 90.85%
86 Hermes 3 70B 78.42% 77.41% 72.57%
87 Writer: Palmyra X5 78.38% 83.95% 79.57%
88 Z.AI GLM 5 Turbo 78.37% 84.66% 94.27%
89 Claude Opus 4 78.30% 83.79% 87.69%
90 GPT-4o Mini (temp=1) 78.20% 74.37% 79.08%
91 DeepSeek V4 Pro (Reasoning) 78.10% 82.99% 90.10%
92 Gemini 2.5 Flash 78.05% 77.57% 80.60%
93 MoonshotAI: Kimi K2.6 77.97% 85.47% 92.31%
94 Cohere Command R+ (Aug. 2024) 77.80% 77.70% 69.03%
95 ByteDance Seed 1.6 77.64% 78.43% 90.70%
96 Xiaomi MIMO v2.5 77.49% 79.16% 85.05%
97 Grok 4 77.48% 77.34% 88.12%
98 Z.AI GLM 5.1 77.47% 84.05% 94.37%
99 Gemini 2.5 Flash (Reasoning) 77.43% 76.30% 86.51%
100 DeepSeek V4 Pro 77.40% 83.70% 82.63%
101 Claude 3.5 Sonnet 77.15% 78.69% 84.24%
102 Gemma 4 31B 76.74% 75.59% 86.91%
103 Claude Sonnet 4.6 76.43% 83.31% 91.15%
104 Claude Sonnet 4.5 76.41% 84.19% 88.03%
105 Gemini 2.5 Flash Lite 76.25% 75.05% 81.08%
106 Xiaomi MIMO v2.5 Pro 76.24% 81.08% 87.36%
107 Ministral 3 8B 76.24% 77.26% 71.76%
108 Mistral Small 4 76.23% 81.12% 76.46%
109 ByteDance Seed 2.0 Lite 76.22% 82.35% 84.80%
110 Mistral Small Creative 76.20% 80.29% 73.27%
111 Mistral Small 4 (Reasoning) 75.97% 81.67% 82.39%
112 Mistral NeMO 75.80% 76.72% 65.04%
113 Claude Opus 4.6 (Reasoning) 75.75% 84.55% 95.02%
114 ByteDance Seed 1.6 Flash 75.52% 81.51% 73.27%
115 MiniMax M2.5 75.41% 81.21% 88.71%
116 Claude Sonnet 4.6 (Reasoning) 75.13% 83.09% 93.66%
117 Stealth: Hunter Alpha 74.96% 79.18% 87.34%
118 LFM2 24B 74.86% 78.10% 58.77%
119 Grok 4 Fast 74.82% 77.03% 86.15%
120 MiniMax M2.7 74.72% 81.70% 89.10%
121 Stealth: Healer Alpha 74.72% 78.28% 85.93%
122 Claude Opus 4.5 73.89% 81.71% 89.69%
123 Arcee AI: Trinity Large (Preview) 73.85% 75.26% 73.33%
124 Ministral 8B 73.81% 76.87% 64.87%
125 Claude Sonnet 4 73.80% 79.21% 88.72%
126 Qwen 2.5 72B 72.84% 75.16% 75.46%
127 GPT-5.4 Nano (Reasoning) 72.62% 80.97% 81.36%
128 Claude Opus 4.6 72.59% 83.59% 92.35%
129 Z.AI GLM 4.5 72.34% 76.56% 86.27%
130 Claude Haiku 4.5 71.93% 78.96% 85.14%
131 Qwen 3.5 Plus (2026-02-15) 71.92% 77.07% 85.96%
132 Cydonia 24B V4.1 71.78% 74.19% 75.09%
133 Llama 3.1 Nemotron 70B 71.70% 71.71% 74.70%
134 Llama 3.1 70B 70.83% 72.78% 78.40%
135 Ministral 3B 70.80% 75.49% 61.29%
136 Ministral 3 3B 70.63% 75.45% 67.22%
137 GPT-4o Mini (temp=0) 70.56% 73.10% 78.29%
138 GPT-OSS 120B 70.48% 67.85% 86.44%
139 GPT-5.4 Nano (Reasoning, Low) 70.47% 80.93% 79.48%
140 GPT-4o, May 13th (temp=0) 69.79% 74.89% 85.36%
141 GPT-5.4 Nano 69.68% 80.50% 74.40%
142 GPT-4o, Aug. 6th (temp=0) 69.33% 73.65% 82.45%
143 Claude 3.7 Sonnet 69.12% 76.31% 83.39%
144 Inception Mercury 68.89% 69.99% 79.50%
145 Claude 3 Haiku 68.71% 74.53% 71.19%
146 Mistral Small 3.2 24B 68.55% 71.87% 78.58%
147 Z.AI GLM 4.5 Air 68.55% 74.61% 83.12%
148 Stealth: Aurora Alpha 68.10% 67.54% 83.79%
149 Inception Mercury 2 67.53% 68.31% 83.85%
150 MoonshotAI: Kimi K2.5 67.36% 81.35% 91.04%
151 Gemini 2.5 Flash Lite (Reasoning) 66.75% 71.64% 85.75%
152 GPT-5.2 66.36% 80.36% 90.26%
153 Nemotron 3 Super 64.41% 69.75% 84.56%
154 Nemotron 3 Nano 64.30% 65.87% 77.73%
155 GPT-5 Nano 50.07% 67.04% 82.60%