// BENCHMARK

Creative Writing v3 benchmark

AI model leaderboard for the Creative Writing v3 benchmark. Compare how large language models score on Creative Writing v3, see the full ranking, and understand what this AI benchmark measures. Qwen3-235B-A22B currently leads with 84.6. Open-ended creative-writing benchmark — LLM judge scores prose quality, originality, and instruction adherence.

Leaderboard

# Model Organization Score Variant Source
#1 Qwen3-235B-A22B Qwen 84.6 thinking official ↗
#2 Qwen3-32B Qwen 81 thinking official ↗
#3 Qwen3-235B-A22B Qwen 80.4 non-thinking official ↗
#4 Qwen3-14B Qwen 80.3 thinking official ↗
#5 Qwen3-30B-A3B Qwen 79.1 thinking official ↗
#6 Qwen3-32B Qwen 78.3 non-thinking official ↗
#7 Qwen3-8B Qwen 75 thinking official ↗
#8 Qwen3-14B Qwen 73.1 non-thinking official ↗
#9 Qwen3-30B-A3B Qwen 68.1 non-thinking official ↗
#10 Qwen3-8B Qwen 64.5 non-thinking official ↗
#11 Qwen3-4B Qwen 61.1 thinking official ↗
#12 Qwen3-4B Qwen 53.6 non-thinking official ↗
#13 Qwen3-1.7B Qwen 48 thinking official ↗
#14 Qwen3-1.7B Qwen 43.6 non-thinking official ↗
#15 Qwen3-0.6B Qwen 30.6 thinking official ↗
#16 Qwen3-0.6B Qwen 28.4 non-thinking official ↗

Frequently asked questions about Creative Writing v3

What is the Creative Writing v3 benchmark?

Open-ended creative-writing benchmark — LLM judge scores prose quality, originality, and instruction adherence.

How is the Creative Writing v3 benchmark scored?

Creative Writing v3 is scored using the rubric_score metric, where a higher score is better. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.

Which AI model scores highest on Creative Writing v3?

As of the latest reported scores on GenAIList, Qwen3-235B-A22B achieves the highest result on Creative Writing v3 with a score of 84.6.

Is a higher Creative Writing v3 score better?

Yes. On Creative Writing v3 a higher score indicates better performance, so models near the top of the leaderboard are the strongest.