NC Bench
Overview
About
Tests
Models
Novel outline
Handle questions about the outline of a novel in various formats
Count point of views for Jack and Olivia (indented)
0-shot
Tooling
Utility
Model
Run 1
Run 2
Run 3
Run 4
Run 5
Run 6
Run 7
Run 8
Run 9
Run 10
Total
GPT-4o, May 13th (temp=0)
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
Llama 3 70B
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
Claude 3.5 Haiku
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
Gemini 3 Pro (Preview)
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
Claude Opus 4.6
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
MoonshotAI: Kimi K2.5
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
GPT-4o, Aug. 6th (temp=0)
100%
100%
100%
100%
100%
100%
100%
100%
100%
50%
95%
Llama 3.1 Nemotron 70B
100%
100%
100%
100%
100%
100%
100%
100%
100%
50%
95%
Z.AI GLM 4.6
100%
100%
100%
100%
100%
100%
100%
100%
100%
50%
95%
Writer: Palmyra X5
100%
100%
100%
100%
100%
100%
100%
100%
100%
50%
95%
GPT-4o, May 13th (temp=1)
100%
100%
100%
100%
100%
100%
100%
100%
50%
50%
90%
GPT-4o, Aug. 6th (temp=1)
100%
100%
100%
100%
100%
100%
100%
100%
50%
50%
90%
Qwen 2 72B
100%
100%
100%
100%
100%
100%
100%
100%
100%
0%
90%
Claude 3.5 Sonnet (new)
100%
100%
100%
100%
100%
100%
100%
100%
50%
50%
90%
Gemini 2.5 Pro
100%
100%
100%
100%
100%
100%
100%
100%
100%
0%
90%
Gemini 2.5 Flash Lite
100%
100%
100%
100%
100%
100%
100%
100%
100%
0%
90%
Z.AI GLM 4.7
100%
100%
100%
100%
100%
100%
100%
100%
100%
0%
90%
Claude 2.1
100%
100%
100%
100%
100%
100%
50%
50%
50%
50%
80%
Claude Sonnet 4
100%
100%
100%
100%
100%
100%
100%
50%
50%
0%
80%
Z.AI GLM 4.5
100%
100%
100%
100%
100%
100%
100%
100%
0%
0%
80%
Mistral Small Creative
100%
100%
100%
100%
100%
100%
50%
50%
50%
50%
80%
Qwen 2.5 72B
100%
100%
100%
100%
100%
50%
50%
50%
50%
50%
75%
GPT-4.1
100%
100%
100%
100%
100%
100%
100%
50%
0%
0%
75%
Claude Opus 4
100%
100%
100%
100%
100%
100%
100%
50%
0%
0%
75%
Z.AI GLM 4.7 Flash
100%
100%
100%
100%
100%
100%
100%
50%
0%
0%
75%
Claude Opus 4.5
100%
100%
100%
100%
100%
50%
50%
50%
50%
0%
70%
WizardLM 2 8x22b
100%
100%
100%
100%
50%
50%
50%
50%
50%
0%
65%
Llama 3.2 11B (Vision)
100%
100%
100%
100%
100%
50%
50%
50%
0%
0%
65%
Magnum v2 72B
100%
100%
100%
100%
100%
100%
50%
0%
0%
0%
65%
MN GRAND Gutenberg Lyra4 12B Madness
100%
100%
100%
100%
100%
50%
50%
50%
0%
0%
65%
GPT-4.1 Nano
100%
100%
100%
50%
50%
50%
50%
50%
50%
50%
65%
Claude 2.0
100%
100%
100%
100%
100%
100%
0%
0%
0%
0%
60%
Llama 3.1 70B
100%
100%
100%
100%
100%
50%
50%
0%
0%
0%
60%
Llama 3.1 405B
100%
100%
100%
100%
50%
50%
50%
50%
0%
0%
60%
o4 Mini
100%
100%
100%
100%
100%
100%
0%
0%
0%
0%
60%
o4 Mini High
100%
100%
100%
100%
100%
100%
0%
0%
0%
0%
60%
DeepSeek-V2 Chat
100%
100%
100%
100%
50%
50%
50%
0%
0%
0%
55%
GPT-4o Mini (temp=0)
100%
50%
50%
50%
50%
50%
50%
50%
50%
50%
55%
GPT-4o Mini (temp=1)
100%
100%
50%
50%
50%
50%
50%
50%
50%
0%
55%
Gemini 2.5 Flash
100%
100%
100%
100%
50%
50%
50%
0%
0%
0%
55%
Gemini 3 Flash (Preview)
100%
50%
50%
50%
50%
50%
50%
50%
50%
50%
55%
Hermes 3 70B
100%
100%
100%
50%
50%
50%
50%
0%
0%
0%
50%
Cohere Command R+ (Aug. 2024)
100%
100%
100%
50%
50%
50%
50%
0%
0%
0%
50%
Claude Haiku 4.5
100%
100%
100%
100%
50%
50%
0%
0%
0%
0%
50%
Goliath 120B
100%
100%
100%
50%
50%
50%
0%
0%
0%
0%
45%
Llama 3.2 90B (Vision)
100%
100%
100%
100%
50%
0%
0%
0%
0%
0%
45%
EVA Qwen 2.5 14B
100%
100%
100%
50%
50%
50%
0%
0%
0%
0%
45%
GPT-4.1 Mini
100%
100%
100%
100%
50%
0%
0%
0%
0%
0%
45%
Hermes 3 405B
100%
100%
50%
50%
50%
50%
0%
0%
0%
0%
40%
Mistral Large 2
100%
100%
50%
50%
50%
50%
0%
0%
0%
0%
40%
Ministral 3B
100%
100%
50%
50%
50%
50%
0%
0%
0%
0%
40%
Ministral 8B
100%
100%
100%
50%
50%
0%
0%
0%
0%
0%
40%
Llama 3 TenyxChat-DaybreakStorywriter 70B
100%
100%
100%
50%
50%
0%
0%
0%
0%
0%
40%
Llama 3.2 3B
100%
100%
100%
50%
0%
0%
0%
0%
0%
0%
35%
Claude 3 Haiku
100%
50%
50%
50%
50%
0%
0%
0%
0%
0%
30%
Gemini Flash 1.5
100%
100%
100%
0%
0%
0%
0%
0%
0%
0%
30%
Claude 3.0 Sonnet
100%
100%
100%
0%
0%
0%
0%
0%
0%
0%
30%
Mistral NeMO
50%
50%
50%
50%
50%
50%
0%
0%
0%
0%
30%
Claude 3.7 Sonnet
100%
100%
50%
0%
0%
0%
0%
0%
0%
0%
25%
lzlv 70B
100%
50%
50%
50%
0%
0%
0%
0%
0%
0%
25%
Llama 3.1 8B
100%
50%
50%
50%
0%
0%
0%
0%
0%
0%
25%
Sao10K L3.1 70B Hanami x1
100%
50%
50%
50%
0%
0%
0%
0%
0%
0%
25%
Magnum 72B
100%
50%
50%
0%
0%
0%
0%
0%
0%
0%
20%
Gemma 2 9B
50%
50%
50%
50%
0%
0%
0%
0%
0%
0%
20%
Gemma 2 27B
50%
50%
50%
50%
0%
0%
0%
0%
0%
0%
20%
Phi-3.5 Mini 128k
100%
50%
50%
0%
0%
0%
0%
0%
0%
0%
20%
Hermes 2 Theta 8B
100%
50%
50%
0%
0%
0%
0%
0%
0%
0%
20%
Qwen 2 7B
100%
50%
50%
0%
0%
0%
0%
0%
0%
0%
20%
Mistral Nemo 12B Celeste
100%
50%
50%
0%
0%
0%
0%
0%
0%
0%
20%
Claude 3.5 Sonnet
50%
50%
50%
0%
0%
0%
0%
0%
0%
0%
15%
Mistral Medium
50%
50%
50%
0%
0%
0%
0%
0%
0%
0%
15%
Fimbulvetr 11B v2
50%
50%
50%
0%
0%
0%
0%
0%
0%
0%
15%
AI21 Jamba 1.5 Large
50%
50%
50%
0%
0%
0%
0%
0%
0%
0%
15%
Rocinante 12B
100%
50%
0%
0%
0%
0%
0%
0%
0%
0%
15%
Phi-3 Medium 128k
50%
50%
0%
0%
0%
0%
0%
0%
0%
0%
10%
Llama 3 Euryale 70B v2.1
50%
50%
0%
0%
0%
0%
0%
0%
0%
0%
10%
Llama 3.1 Euryale 70B v2.2
50%
50%
0%
0%
0%
0%
0%
0%
0%
0%
10%
MythoMax 13B
50%
50%
0%
0%
0%
0%
0%
0%
0%
0%
10%
Toppy M 7B
50%
50%
0%
0%
0%
0%
0%
0%
0%
0%
10%
GPT-4 Turbo
100%
0%
0%
0%
0%
0%
0%
0%
0%
0%
10%
AI21 Jamba 1.5 Mini
50%
50%
0%
0%
0%
0%
0%
0%
0%
0%
10%
Liquid: LFM 40B MoE
50%
50%
0%
0%
0%
0%
0%
0%
0%
0%
10%
Claude Sonnet 4.5
50%
50%
0%
0%
0%
0%
0%
0%
0%
0%
10%
Phi-3 Mini 128k
50%
0%
0%
0%
0%
0%
0%
0%
0%
0%
5%
AI21 Jamba
50%
0%
0%
0%
0%
0%
0%
0%
0%
0%
5%
MythoMist 7B
50%
0%
0%
0%
0%
0%
0%
0%
0%
0%
5%
Llama 3.2 1B
50%
0%
0%
0%
0%
0%
0%
0%
0%
0%
5%
Lumimaid v0.2 8B
50%
0%
0%
0%
0%
0%
0%
0%
0%
0%
5%
Inflection 3 (Productivity)
50%
0%
0%
0%
0%
0%
0%
0%
0%
0%
5%
Gemini Pro 1.5
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Cohere Command R+ (Apr. 2024)
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Mistral Large
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
Inflection 3 (PI)
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
0%
46.45%