NC Bench
Overview
About
Tests
Models
Write N of X
Write exactly N words/sentences/paragraphs...
50 word summary
0-shot
Rule following
Model
Run 1
Run 2
Run 3
Run 4
Run 5
Run 6
Run 7
Run 8
Run 9
Run 10
Total
Gemini 3 Pro (Preview)
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
o4 Mini High
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
Z.AI GLM 4.7
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
Z.AI GLM 4.7 Flash
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
GPT-4o Mini (temp=0)
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
MoonshotAI: Kimi K2.5
100%
100%
100%
100%
100%
100%
100%
100%
100%
98%
100%
Gemini 2.5 Pro
100%
100%
100%
100%
100%
100%
100%
98%
98%
98%
99%
Gemini 3 Flash (Preview)
100%
100%
100%
100%
100%
100%
100%
98%
98%
98%
99%
GPT-4o, Aug. 6th (temp=0)
100%
100%
100%
100%
100%
100%
100%
98%
98%
98%
99%
Llama 3.1 405B
100%
100%
100%
100%
100%
100%
100%
98%
98%
92%
99%
GPT-4o, May 13th (temp=0)
98%
98%
98%
98%
98%
98%
98%
98%
98%
98%
98%
Claude Opus 4.5
100%
100%
100%
100%
100%
100%
100%
98%
92%
92%
98%
Claude Opus 4
100%
100%
100%
100%
100%
100%
98%
98%
92%
92%
98%
GPT-4o Mini (temp=1)
100%
100%
100%
100%
100%
98%
98%
98%
92%
92%
98%
GPT-4o, May 13th (temp=1)
100%
100%
100%
100%
100%
98%
98%
98%
98%
77%
97%
o4 Mini
100%
100%
100%
100%
100%
100%
100%
98%
92%
77%
97%
Claude Opus 4.6
100%
100%
98%
98%
98%
98%
98%
98%
98%
77%
97%
Llama 3 70B
100%
100%
100%
100%
100%
98%
98%
92%
92%
77%
96%
GPT-4.1 Mini
100%
100%
100%
100%
100%
98%
98%
92%
92%
77%
96%
Z.AI GLM 4.6
100%
100%
100%
100%
100%
100%
98%
98%
77%
77%
95%
Llama 3.1 Nemotron 70B
100%
100%
100%
100%
100%
98%
98%
98%
98%
54%
95%
GPT-4o, Aug. 6th (temp=1)
100%
100%
100%
100%
100%
98%
98%
98%
92%
54%
94%
Llama 3.1 70B
100%
100%
100%
100%
100%
92%
77%
77%
77%
54%
88%
GPT-4.1 Nano
100%
100%
100%
98%
98%
98%
98%
92%
54%
27%
87%
Gemini 2.5 Flash Lite
100%
100%
100%
98%
98%
92%
92%
92%
77%
2%
85%
GPT-4.1
100%
100%
100%
98%
98%
92%
92%
77%
54%
27%
84%
Claude Sonnet 4.5
100%
100%
100%
100%
100%
98%
77%
77%
27%
0%
78%
Claude 3.7 Sonnet
100%
98%
98%
98%
98%
92%
77%
54%
27%
27%
77%
AI21 Jamba 1.5 Large
100%
100%
100%
100%
100%
98%
92%
77%
0%
0%
77%
Llama 3.2 3B
100%
100%
100%
100%
98%
92%
92%
54%
27%
0%
76%
Sao10K L3.1 70B Hanami x1
100%
98%
98%
98%
92%
92%
92%
54%
0%
0%
73%
Llama 3 TenyxChat-DaybreakStorywriter 70B
100%
98%
98%
92%
92%
77%
77%
54%
9%
2%
70%
Claude 3.5 Sonnet
100%
100%
100%
98%
77%
54%
54%
54%
54%
9%
70%
Llama 3.2 90B (Vision)
100%
100%
100%
100%
98%
98%
54%
27%
9%
0%
69%
Cohere Command R+ (Apr. 2024)
100%
100%
100%
98%
92%
92%
77%
9%
9%
2%
68%
Claude 3.5 Sonnet (new)
92%
92%
77%
77%
77%
77%
54%
54%
54%
9%
66%
Llama 3.2 11B (Vision)
100%
100%
98%
98%
98%
77%
54%
0%
0%
0%
63%
Hermes 3 405B
100%
100%
100%
98%
92%
92%
27%
9%
2%
0%
62%
Claude Haiku 4.5
100%
100%
100%
92%
77%
54%
54%
27%
9%
0%
61%
GPT-4 Turbo
100%
100%
98%
92%
54%
54%
54%
27%
27%
0%
61%
Z.AI GLM 4.5
100%
100%
98%
92%
92%
27%
27%
27%
9%
2%
58%
Llama 3.1 8B
100%
98%
98%
92%
77%
54%
54%
0%
0%
0%
57%
Claude 2.1
100%
100%
92%
77%
77%
54%
27%
2%
0%
0%
53%
Claude Sonnet 4
98%
92%
92%
77%
54%
54%
27%
9%
0%
0%
50%
Gemini Pro 1.5
100%
100%
92%
77%
54%
9%
9%
2%
0%
0%
44%
Llama 3.2 1B
100%
100%
100%
77%
27%
27%
9%
0%
0%
0%
44%
Qwen 2.5 72B
100%
98%
77%
77%
54%
27%
2%
0%
0%
0%
44%
Mistral Large 2
98%
92%
77%
54%
54%
27%
0%
0%
0%
0%
40%
Phi-3.5 Mini 128k
100%
100%
100%
92%
0%
0%
0%
0%
0%
0%
39%
Ministral 8B
100%
92%
92%
77%
9%
9%
0%
0%
0%
0%
38%
Claude 3.0 Sonnet
92%
92%
92%
54%
27%
9%
9%
0%
0%
0%
38%
Mistral NeMO
98%
92%
92%
54%
27%
2%
0%
0%
0%
0%
37%
Inflection 3 (Productivity)
100%
98%
98%
27%
27%
9%
2%
0%
0%
0%
36%
Inflection 3 (PI)
100%
77%
54%
54%
54%
2%
0%
0%
0%
0%
34%
AI21 Jamba 1.5 Mini
100%
92%
54%
27%
27%
9%
9%
0%
0%
0%
32%
Gemma 2 9B
100%
77%
77%
54%
2%
0%
0%
0%
0%
0%
31%
Phi-3 Mini 128k
100%
98%
98%
9%
0%
0%
0%
0%
0%
0%
31%
AI21 Jamba
100%
100%
54%
9%
0%
0%
0%
0%
0%
0%
26%
lzlv 70B
100%
92%
9%
0%
0%
0%
0%
0%
0%
0%
20%
Liquid: LFM 40B MoE
100%
54%
0%
0%
0%
0%
0%
0%
0%
0%
15%
Gemma 2 27B
98%
54%
0%
0%
0%
0%
0%
0%
0%
0%
15%
DeepSeek-V2 Chat
54%
27%
27%
9%
9%
9%
0%
0%
0%
0%
14%
EVA Qwen 2.5 14B
98%
27%
9%
0%
0%
0%
0%
0%
0%
0%
13%
Goliath 120B
100%
27%
0%
0%
0%
0%
0%
0%
0%
0%
13%
Lumimaid v0.2 8B
100%
2%
2%
0%
0%
0%
0%
0%
0%
0%
10%
Gemini Flash 1.5
100%
2%
0%
0%
0%
0%
0%
0%
0%
0%
10%
Mistral Medium
98%
2%
0%
0%
0%
0%
0%
0%
0%
0%
10%
Llama 3 Euryale 70B v2.1
98%
0%
0%
0%
0%
0%
0%
0%
0%
0%
10%
Phi-3 Medium 128k
77%
2%
0%
0%
0%
0%
0%
0%
0%
0%
8%
Claude 2.0
54%
0%
0%
0%
0%
0%
0%
0%
0%
0%
5%
Llama 3.1 Euryale 70B v2.2
54%
0%
0%
0%
0%
0%
0%
0%
0%
0%
5%
MythoMist 7B
54%
0%
0%
0%
0%
0%
0%
0%
0%
0%
5%
Ministral 3B
27%
2%
2%
2%
0%
0%
0%
0%
0%
0%
3%
Claude 3.5 Haiku
27%
2%
0%
0%
0%
0%
0%
0%
0%
0%
3%
Magnum v2 72B
27%
0%
0%
0%
0%
0%
0%
0%
0%
0%
3%
Mistral Large
9%
0%
0%
0%
0%
0%
0%
0%
0%
0%
1%
Writer: Palmyra X5
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Gemini 2.5 Flash
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Qwen 2 7B
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Rocinante 12B
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Cohere Command R+ (Aug. 2024)
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Hermes 3 70B
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Claude 3 Haiku
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Magnum 72B
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Mistral Small Creative
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
MN GRAND Gutenberg Lyra4 12B Madness
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Hermes 2 Theta 8B
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
MythoMax 13B
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Fimbulvetr 11B v2
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
WizardLM 2 8x22b
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Qwen 2 72B
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Toppy M 7B
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Mistral Nemo 12B Celeste
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
46.94%