creativity benchmark
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 7, 2026
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 87.5% | 100.0% | 13 | C | |
| 2 | AC | 86.5% | 91.7% | 13 | C | |
| 3 | AC | 86.1% | 83.3% | 13 | C | |
| 4 | XA | 86.1% | 75.0% | 13 | C | |
| 5 | AC | 85.7% | 66.7% | 13 | C | |
| 6 | AC | 85.6% | 58.3% | 13 | C | |
| 7 | XA | 85.4% | 50.0% | 13 | C | |
| 8 | AC | 85.3% | 41.7% | 13 | C | |
| 9 | AC | 84.6% | 33.3% | 13 | C | |
| 10 | AC | 83.3% | 25.0% | 13 | C | |
| 11 | AC | 82.5% | 16.7% | 13 | C | |
| 12 | AC | 82.4% | 8.3% | 13 | C | |
| 13 | AC | 76.1% | 0.0% | 13 | C |
Top published rows on the benchmark's original scale.
The top published results on this benchmark's own scale.
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level B.
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
Common questions about Creative Writing v3.
Qwen3-235B-A22B-Instruct-2507 is currently ranked first with 87.5%.
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.
Yes. Higher values rank better for this benchmark.
13 unique published model results are currently shown.
This benchmark is marked as eligible for the current LLMBoard capability methodology.