llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeBenchmarkscreativityCreative Writing v3

creativity benchmark

Creative Writing v3

EQ-Bench Creative Writing v3 is an LLM-judged creative writing benchmark that evaluates models across 32 writing prompts with 3 iterations per prompt. Uses a hybrid scoring system combining rubric assessment and Elo ratings through pairwise comparisons. Challenges models in areas like humor, romance, spatial awareness, and unique perspectives to assess emotional intelligence and creative writing capabilities.

Updated Aug 11, 2026

Models13
Model coverage13
MetricScore
EvidenceB

On this page

  • Ranking
  • Distribution
  • Highlights
  • About
  • FAQ

Creative Writing v3 Ranking

Higher score ranks better on this benchmark.

13 rows
Columns

Show columns

1ACQwen3-235B-A22B-Instruct-2507Alibaba Cloud / Qwen Team87.5%100.0%13CAug 11, 2026
2ACQwen3 VL 235B A22B InstructAlibaba Cloud / Qwen Team86.5%91.7%13CAug 11, 2026
3ACQwen3-235B-A22B-Thinking-2507Alibaba Cloud / Qwen Team86.1%83.3%13CAug 11, 2026
4XAGrok-4.1 ThinkingxAI86.1%75.0%13CAug 11, 2026
5ACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen Team85.7%66.7%13CAug 11, 2026
6ACQwen3 VL 32B InstructAlibaba Cloud / Qwen Team85.6%58.3%13CAug 11, 2026
7XAGrok-4.1xAI85.4%50.0%13CAug 11, 2026
8ACQwen3-Next-80B-A3B-InstructAlibaba Cloud / Qwen Team85.3%41.7%13CAug 11, 2026
9ACQwen3 VL 30B A3B InstructAlibaba Cloud / Qwen Team84.6%33.3%13CAug 11, 2026
10ACQwen3 VL 32B ThinkingAlibaba Cloud / Qwen Team83.3%25.0%13CAug 11, 2026
11ACQwen3 VL 30B A3B ThinkingAlibaba Cloud / Qwen Team82.5%16.7%13CAug 11, 2026
12ACQwen3 VL 8B ThinkingAlibaba Cloud / Qwen Team82.4%8.3%13CAug 11, 2026
13ACQwen3 VL 4B ThinkingAlibaba Cloud / Qwen Team76.1%0.0%13CAug 11, 2026

Creative Writing v3 Score Distribution

A closer view of the leading scores on this benchmark.

Creative Writing v3

Creative Writing v3 Highlights

The leading models and scores on this benchmark.

Rank #1Qwen3-235B-A22B-Instruct-250787.5%Rank #2Qwen3 VL 235B A22B Instruct86.5%Rank #3Qwen3-235B-A22B-Thinking-250786.1%Rank #4Grok-4.1 Thinking86.1%

What is Creative Writing v3?

What Creative Writing v3 measures and how its scores work.

EQ-Bench Creative Writing v3 is an LLM-judged creative writing benchmark that evaluates models across 32 writing prompts with 3 iterations per prompt. Uses a hybrid scoring system combining rubric assessment and Elo ratings through pairwise comparisons. Challenges models in areas like humor, romance, spatial awareness, and unique perspectives to assess emotional intelligence and creative writing capabilities.

Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.

Family
Creative Writing v3
Modality
text
Primary category
creativity
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
creative-writing-v3|llm-stats-current

Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about Creative Writing v3.

Which model scores highest on Creative Writing v3?

Qwen3-235B-A22B-Instruct-2507 is currently ranked first with 87.5%.

What does Creative Writing v3 measure?

EQ-Bench Creative Writing v3 is an LLM-judged creative writing benchmark that evaluates models across 32 writing prompts with 3 iterations per prompt. Uses a hybrid scoring system combining rubric assessment and Elo ratings through pairwise comparisons. Challenges models in areas like humor, romance, spatial awareness, and unique perspectives to assess emotional intelligence and creative writing capabilities.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

13 model results are currently shown.

Does this benchmark affect the overall score?

Yes. This benchmark can contribute to the current LLMBoard capability score.

Rankings

OverallCodingText ArenaPricing

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai