Write N of X

Write exactly N words/sentences/paragraphs...

100 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
Z.AI GLM 4.7100%100%100%100%100%100%100%100%100%100%100%
GPT-4o Mini (temp=1)100%100%100%100%100%100%100%100%98%98%100%
Gemini 3 Pro (Preview)100%100%100%100%100%100%100%98%98%92%99%
MoonshotAI: Kimi K2.5100%100%100%100%100%98%98%98%98%92%99%
GPT-4o, Aug. 6th (temp=0)100%100%100%100%98%98%98%98%98%92%98%
Gemini 3 Flash (Preview)100%100%100%100%98%98%98%98%98%92%98%
o4 Mini High100%100%100%98%98%98%98%98%92%92%98%
Gemini 2.5 Pro100%100%98%98%98%98%98%92%92%92%97%
Z.AI GLM 4.7 Flash100%100%100%98%98%98%92%92%92%92%96%
Claude Opus 4.5100%100%100%100%100%98%98%92%92%77%96%
o4 Mini100%100%100%100%100%98%92%92%92%77%95%
GPT-4.1100%100%100%100%100%100%98%98%77%77%95%
GPT-4o Mini (temp=0)100%92%92%92%92%92%92%92%92%92%93%
GPT-4o, May 13th (temp=0)100%100%100%100%100%98%98%92%77%27%89%
Claude Opus 4.6100%100%100%100%100%98%98%77%54%54%88%
GPT-4.1 Mini100%100%98%98%98%92%92%92%54%54%88%
Z.AI GLM 4.6100%100%100%98%98%92%92%92%54%27%85%
Claude 3.7 Sonnet100%100%100%100%98%98%98%77%54%27%85%
GPT-4o, Aug. 6th (temp=1)100%100%100%100%98%92%92%54%54%54%84%
Llama 3.1 405B100%100%100%100%100%100%92%92%27%0%81%
Llama 3.1 70B100%100%98%98%98%92%77%77%54%2%80%
GPT-4o, May 13th (temp=1)100%100%100%98%98%92%92%77%27%9%79%
Llama 3 TenyxChat-DaybreakStorywriter 70B100%100%100%98%98%77%77%77%54%9%79%
Claude Sonnet 498%98%98%98%77%77%77%77%9%0%71%
Claude 3.5 Sonnet100%98%98%92%92%77%77%54%2%0%69%
Gemini 2.5 Flash Lite100%100%98%92%92%92%54%54%9%0%69%
Claude Sonnet 4.5100%100%98%92%92%77%54%27%9%0%65%
Llama 3.2 90B (Vision)100%100%98%98%98%98%27%9%9%2%64%
Claude Opus 4100%98%98%92%77%54%54%27%27%0%63%
Llama 3 70B100%100%100%98%92%92%27%9%2%0%62%
Hermes 3 405B100%100%98%98%92%92%27%2%0%0%61%
Mistral Large 2100%100%100%92%77%77%0%0%0%0%55%
Z.AI GLM 4.5100%100%98%77%54%27%27%27%0%0%51%
Llama 3.1 Nemotron 70B100%98%92%92%54%54%9%9%2%0%51%
Claude 2.1100%100%100%98%27%27%27%0%0%0%48%
Llama 3.1 8B100%98%92%92%77%9%0%0%0%0%47%
GPT-4.1 Nano100%98%77%77%54%54%2%2%0%0%46%
AI21 Jamba 1.5 Large92%92%77%77%54%27%9%2%0%0%43%
Claude 3.0 Sonnet100%100%100%92%0%0%0%0%0%0%39%
Mistral Large100%100%100%54%27%9%0%0%0%0%39%
Mistral Medium100%98%98%27%27%27%0%0%0%0%38%
Llama 3.2 3B100%92%77%54%27%9%0%0%0%0%36%
Llama 3.2 1B100%92%92%27%27%9%0%0%0%0%35%
Claude 3.5 Sonnet (new)100%92%54%54%27%9%2%0%0%0%34%
Gemini 2.5 Flash100%100%77%27%0%0%0%0%0%0%30%
Qwen 2.5 72B100%100%92%9%2%0%0%0%0%0%30%
Gemini Pro 1.5100%92%54%27%0%0%0%0%0%0%27%
Llama 3.2 11B (Vision)92%77%77%9%0%0%0%0%0%0%26%
Magnum v2 72B100%98%27%9%0%0%0%0%0%0%23%
Sao10K L3.1 70B Hanami x1100%54%54%27%0%0%0%0%0%0%23%
DeepSeek-V2 Chat98%92%27%2%2%0%0%0%0%0%22%
Hermes 3 70B98%92%9%2%0%0%0%0%0%0%20%
EVA Qwen 2.5 14B100%54%27%9%0%0%0%0%0%0%19%
Phi-3 Medium 128k77%77%27%0%0%0%0%0%0%0%18%
Gemini Flash 1.598%54%27%2%0%0%0%0%0%0%18%
Hermes 2 Theta 8B98%77%0%0%0%0%0%0%0%0%18%
Cohere Command R+ (Apr. 2024)77%77%0%0%0%0%0%0%0%0%15%
Claude Haiku 4.5100%54%0%0%0%0%0%0%0%0%15%
Phi-3.5 Mini 128k92%54%0%0%0%0%0%0%0%0%15%
AI21 Jamba77%54%2%0%0%0%0%0%0%0%13%
Qwen 2 72B77%54%0%0%0%0%0%0%0%0%13%
Gemma 2 9B98%9%0%0%0%0%0%0%0%0%11%
GPT-4 Turbo98%9%0%0%0%0%0%0%0%0%11%
AI21 Jamba 1.5 Mini100%2%0%0%0%0%0%0%0%0%10%
Ministral 3B100%0%0%0%0%0%0%0%0%0%10%
Gemma 2 27B100%0%0%0%0%0%0%0%0%0%10%
Qwen 2 7B100%0%0%0%0%0%0%0%0%0%10%
Mistral Nemo 12B Celeste100%0%0%0%0%0%0%0%0%0%10%
Ministral 8B98%0%0%0%0%0%0%0%0%0%10%
Claude 2.092%2%0%0%0%0%0%0%0%0%9%
Cohere Command R+ (Aug. 2024)54%27%9%2%0%0%0%0%0%0%9%
Claude 3.5 Haiku77%9%0%0%0%0%0%0%0%0%9%
Mistral Small Creative54%0%0%0%0%0%0%0%0%0%5%
Llama 3.1 Euryale 70B v2.254%0%0%0%0%0%0%0%0%0%5%
Fimbulvetr 11B v227%2%0%0%0%0%0%0%0%0%3%
Toppy M 7B27%0%0%0%0%0%0%0%0%0%3%
Writer: Palmyra X59%9%0%0%0%0%0%0%0%0%2%
Inflection 3 (Productivity)9%2%0%0%0%0%0%0%0%0%1%
Lumimaid v0.2 8B2%0%0%0%0%0%0%0%0%0%0%
Llama 3 Euryale 70B v2.12%0%0%0%0%0%0%0%0%0%0%
Magnum 72B2%0%0%0%0%0%0%0%0%0%0%
MythoMax 13B2%0%0%0%0%0%0%0%0%0%0%
Goliath 120B0%0%0%0%0%0%0%0%0%0%0%
Inflection 3 (PI)0%0%0%0%0%0%0%0%0%0%0%
Phi-3 Mini 128k0%0%0%0%0%0%0%0%0%0%0%
lzlv 70B0%0%0%0%0%0%0%0%0%0%0%
Liquid: LFM 40B MoE0%0%0%0%0%0%0%0%0%0%0%
Mistral NeMO0%0%0%0%0%0%0%0%0%0%0%
MythoMist 7B0%0%0%0%0%0%0%0%0%0%0%
Rocinante 12B0%0%0%0%0%0%0%0%0%0%0%
Claude 3 Haiku0%0%0%0%0%0%0%0%0%0%0%
WizardLM 2 8x22b0%0%0%0%0%0%0%0%0%0%0%
MN GRAND Gutenberg Lyra4 12B Madness0%0%0%0%0%0%0%0%0%0%0%
39.42%