creativity benchmark
Creative Writing v3 Leaderboard
Creative Writing v3 is an LLM-judged creative writing benchmark covering 32 writing prompts with 3 iterations per prompt.
Updated Sep 5, 2026
Models13
Model coverage13
MetricScore
EvidenceB
Creative Writing v3 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score87.50% | Percentile100.00% | Participants13 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score86.50% | Percentile91.67% | Participants13 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score86.10% | Percentile83.33% | Participants13 | EvidenceC | Evaluated |
| Rank04 | ModelXA | Score86.10% | Percentile75.00% | Participants13 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score85.70% | Percentile66.67% | Participants13 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score85.60% | Percentile58.33% | Participants13 | EvidenceC | Evaluated |
| Rank07 | ModelXA | Score85.43% | Percentile50.00% | Participants13 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score85.30% | Percentile41.67% | Participants13 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score84.60% | Percentile33.33% | Participants13 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score83.30% | Percentile25.00% | Participants13 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score82.50% | Percentile16.67% | Participants13 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score82.40% | Percentile8.33% | Participants13 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score76.10% | Percentile0.00% | Participants13 | EvidenceC | Evaluated |
Creative Writing v3 Highlights
The leading models and scores on this benchmark.
Creative Writing v3 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Creative Writing v3
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Creative Writing v3?
What Creative Writing v3 measures and how its scores work.
Creative Writing v3 evaluates language models using a hybrid scoring system that combines rubric assessment with Elo ratings from pairwise comparisons.
It measures performance in creative writing areas including humor, romance, spatial awareness, unique perspectives, and emotional intelligence using the Score metric reported as a ratio.
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
- No
- Evaluation key
- overall
LLM Stats. 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 87.50%.
What are the top three models on Creative Writing v3?
The current leaders are Qwen3-235B-A22B-Instruct-2507 (87.50%), Qwen3 VL 235B A22B Instruct (86.50%), and Qwen3-235B-A22B-Thinking-2507 (86.10%).
Which Creative Writing v3 model has the lowest official input price?
Qwen3-Next-80B-A3B-Instruct has the lowest matched official input price at $0.50 input / $2.0 output per 1M tokens.
Which models are fastest among Creative Writing v3 results?
The fastest matched records are Grok-4.1 (100.00 tok/s via xAI), Grok-4.1 Thinking (80.00 tok/s via xAI), and Qwen3 VL 4B Thinking (8.77 tok/s via DeepInfra).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.