Benchmark
Creative Writing v3 Benchmark
What is 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…
- Modality
- text
- Evaluates
- creativity, writing
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 13
Source provenance
Creative Writing v3 results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Grok-4.1 | xAI | 0.8543 | 2025-11-17 | evidence |
| Grok-4.1 Thinking | xAI | 0.86095 | 2025-11-17 | evidence |
| Qwen3 VL 235B A22B Instruct | Qwen | 0.865 | 2025-09-22 | evidence |
| Qwen3 VL 235B A22B Thinking | Qwen | 0.857 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Instruct | Qwen | 0.846 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Thinking | Qwen | 0.825 | 2025-09-22 | evidence |
| Qwen3 VL 32B Instruct | Qwen | 0.856 | 2025-09-22 | evidence |
| Qwen3 VL 32B Thinking | Qwen | 0.833 | 2025-09-22 | evidence |
| Qwen3 VL 4B Thinking | Qwen | 0.761 | 2025-09-22 | evidence |
| Qwen3 VL 8B Thinking | Qwen | 0.824 | 2025-09-22 | evidence |
| Qwen3-235B-A22B-Instruct-2507 | Qwen | 0.875 | 2025-07-22 | evidence |
| Qwen3-235B-A22B-Thinking-2507 | Qwen | 0.861 | 2025-07-25 | evidence |
| Qwen3-Next-80B-A3B-Instruct | Qwen | 0.853 | 2025-09-10 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.