Sentence Counting

Subcategory of Utility. 118 models scored.

Model Leaderboard

All models ranked by their Sentence Counting subcategory score.

# Model Sentence Counting Utility Overall
1 Gemini 3.1 Pro (Preview) 100.00% 99.91% 94.37%
2 GPT-5 100.00% 93.53% 91.93%
3 Qwen 3.5 397B A17B 100.00% 97.50% 91.73%
4 Qwen 3.5 122B 100.00% 96.36% 91.53%
5 GPT-5.4 (Reasoning, Low) 100.00% 95.32% 91.41%
6 Z.AI GLM 5 100.00% 94.11% 91.23%
7 Qwen 3.5 35B 100.00% 96.42% 88.00%
8 Qwen 3.5 Flash 100.00% 96.11% 86.38%
9 Qwen 3.5 9B 100.00% 94.02% 86.05%
10 Qwen 3.5 Plus (2026-02-15) 100.00% 86.65% 85.96%
11 GPT-5.4 100.00% 81.95% 84.32%
12 GPT-5.4 (Reasoning) 100.00% 96.89% 93.24%
13 GPT-5 Mini 100.00% 98.39% 92.62%
14 Grok 4.20 (Beta, Reasoning) 100.00% 95.41% 91.49%
15 MoonshotAI: Kimi K2.5 100.00% 96.63% 91.04%
16 ByteDance Seed 1.6 100.00% 90.83% 90.70%
17 Claude Opus 4.6 (Reasoning) 100.00% 98.93% 95.02%
18 Z.AI GLM 5 Turbo 100.00% 96.36% 94.27%
19 GPT-5.4 Mini (Reasoning) 100.00% 94.44% 90.65%
20 Gemini 3 Flash (Preview, Reasoning) 100.00% 97.20% 90.50%
21 Z.AI GLM 4.7 Flash 100.00% 88.98% 84.82%
22 Z.AI GLM 4.7 99.99% 94.31% 88.69%
23 Llama 3.1 Nemotron 70B 99.99% 88.31% 74.70%
24 Gemini 3 Flash (Preview) 99.99% 86.39% 85.35%
25 Gemini 3 Pro (Preview) 99.97% 96.14% 88.79%
26 Mistral Small 3.2 24B 99.97% 73.17% 78.60%
27 Claude Sonnet 4.6 (Reasoning) 99.96% 97.88% 93.66%
28 ByteDance Seed 2.0 Lite 99.96% 92.23% 84.80%
29 ByteDance Seed 2.0 Mini 99.96% 91.88% 86.91%
30 Mistral Large 3 99.95% 84.91% 85.43%
31 Claude Opus 4.6 99.93% 90.72% 92.35%
32 GPT-5.4 Mini (Reasoning, Low) 99.92% 88.49% 85.75%
33 o4 Mini High 99.90% 98.67% 90.29%
34 GPT-5.1 99.80% 95.33% 92.54%
35 GPT-5.2 99.77% 96.22% 90.26%
36 Gemini 2.5 Pro 99.43% 92.18% 88.53%
37 Grok 4.20 (Beta) 99.42% 82.15% 83.85%
38 Gemini 3.1 Flash Lite (Preview) 98.60% 94.00% 85.87%
39 o4 Mini 98.35% 96.31% 88.35%
40 GPT-5.4 Mini 98.23% 79.37% 82.43%
41 GPT-5 Nano 97.99% 93.91% 82.60%
42 Nemotron 3 Super 97.96% 95.29% 84.56%
43 DeepSeek V3 (2025-03-24) 97.96% 80.62% 81.99%
44 DeepSeek-V2 Chat 97.87% 83.82% 84.83%
45 Z.AI GLM 4.6 97.70% 88.58% 89.11%
46 Stealth: Aurora Alpha 97.37% 92.59% 83.79%
47 Mistral Medium 3.1 97.23% 80.13% 77.83%
48 Inception Mercury 2 97.02% 92.86% 83.85%
49 Mistral Small Creative 96.83% 76.28% 73.27%
50 Inception Mercury 96.78% 87.38% 79.50%
51 Gemini 2.5 Flash Lite (Reasoning) 96.54% 89.63% 85.75%
52 Mistral Small 4 (Reasoning) 96.06% 85.61% 82.39%
53 Claude Opus 4.5 95.88% 89.84% 89.69%
54 GPT-5.4 Nano (Reasoning) 95.83% 93.34% 81.36%
55 Qwen 3 32B 95.82% 81.66% 82.21%
56 Grok 4.1 Fast 95.61% 84.12% 89.55%
57 MiniMax M2.7 95.47% 95.50% 89.10%
58 Gemma 3 27B 95.44% 76.82% 77.85%
59 Gemma 3 4B 95.04% 60.30% 68.57%
60 Claude Sonnet 4.6 94.66% 88.52% 91.15%
61 GPT-5.4 Nano 93.46% 78.57% 74.40%
62 Claude 3.5 Sonnet 93.24% 76.75% 84.24%
63 GPT-5.4 Nano (Reasoning, Low) 93.19% 91.42% 79.48%
64 Nemotron 3 Nano 92.81% 86.00% 77.73%
65 Qwen 3.5 27B 92.55% 95.67% 90.85%
66 Ministral 3 14B 92.10% 79.03% 72.54%
67 DeepSeek V3.2 92.09% 81.58% 82.25%
68 Claude Sonnet 4.5 91.98% 83.78% 88.03%
69 Stealth: Healer Alpha 90.46% 82.30% 85.93%
70 Grok 4 Fast 89.92% 76.76% 86.15%
71 Aion 2.0 89.10% 90.91% 89.21%
72 DeepSeek V3 (2024-12-26) 88.56% 81.87% 83.68%
73 Grok 4 88.00% 89.67% 88.12%
74 Stealth: Hunter Alpha 87.94% 84.63% 87.34%
75 GPT-4.1 86.01% 90.57% 88.68%
76 Mistral Small 4 85.82% 78.28% 76.46%
77 Llama 3.1 8B 85.64% 74.82% 63.37%
78 Gemini 2.5 Flash (Reasoning) 85.21% 82.25% 86.51%
79 Claude Sonnet 4 84.17% 84.02% 88.72%
80 DeepSeek V3.1 83.32% 76.65% 82.39%
81 ByteDance Seed 1.6 Flash 82.27% 84.16% 73.27%
82 Qwen3 235B A22B Instruct 2507 80.58% 83.15% 80.10%
83 Llama 3.1 70B 80.53% 81.03% 78.40%
84 Claude Opus 4 80.19% 88.81% 87.69%
85 Gemma 3 12B 80.06% 79.28% 78.41%
86 Hermes 3 405B 79.99% 69.02% 82.86%
87 Writer: Palmyra X5 79.93% 79.71% 79.57%
88 GPT-4o Mini (temp=1) 79.62% 82.16% 79.08%
89 GPT-4o Mini (temp=0) 79.49% 81.43% 78.29%
90 GPT-4.1 Mini 79.41% 82.30% 83.20%
91 Claude 3.5 Haiku 76.84% 82.57% 83.73%
92 MiniMax M2.5 75.58% 90.42% 88.71%
93 GPT-4.1 Nano 75.17% 68.45% 71.94%
94 Ministral 3 3B 74.85% 72.38% 67.22%
95 Z.AI GLM 4.5 74.82% 79.19% 86.27%
96 GPT-4o, Aug. 6th (temp=1) 74.24% 82.44% 82.62%
97 Ministral 3 8B 74.12% 74.43% 71.76%
98 GPT-4o, May 13th (temp=1) 74.04% 80.69% 83.80%
99 GPT-4o, Aug. 6th (temp=0) 74.00% 82.11% 82.45%
100 Gemini 2.5 Flash Lite 73.32% 80.14% 81.08%
101 GPT-4o, May 13th (temp=0) 71.82% 83.13% 85.36%
102 WizardLM 2 8x22b 71.48% 67.14% 71.07%
103 Claude Haiku 4.5 70.28% 72.48% 85.14%
104 Qwen 2.5 72B 66.70% 76.43% 75.46%
105 Claude 3.7 Sonnet 66.35% 62.54% 83.39%
106 Gemini 2.5 Flash 64.79% 61.45% 80.60%
107 LFM2 24B 63.93% 69.48% 58.77%
108 Mistral Large 63.80% 73.04% 80.15%
109 Ministral 3B 62.17% 49.17% 61.29%
110 Claude 3 Haiku 61.88% 68.47% 71.19%
111 Cohere Command R+ (Aug. 2024) 60.43% 59.51% 69.03%
112 Ministral 8B 60.35% 46.82% 64.87%
113 Mistral Large 2 58.78% 69.19% 82.41%
114 Hermes 3 70B 58.14% 61.15% 72.57%
115 Arcee AI: Trinity Large (Preview) 57.16% 60.74% 73.33%
116 Rocinante 12B 53.12% 48.47% 54.55%
117 Mistral NeMO 47.57% 51.55% 65.04%
118 Arcee AI: Trinity Mini 43.97% 59.94% 70.90%