Benchmark
WritingBench
A comprehensive benchmark for evaluating large language models' generative writing capabilities across 6 core writing domains (Academic & Engineering…
- Modality
- text
- Categories
- legal, finance, communication, creativity, writing
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 15
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Kimi K2-Thinking-0905 | Moonshot AI | 0.738 | 2025-09-05 | evidence |
| Qwen3 VL 235B A22B Instruct | Qwen | 0.855 | 2025-09-22 | evidence |
| Qwen3 VL 235B A22B Thinking | Qwen | 0.867 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Instruct | Qwen | 0.826 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Thinking | Qwen | 0.852 | 2025-09-22 | evidence |
| Qwen3 VL 32B Instruct | Qwen | 0.829 | 2025-09-22 | evidence |
| Qwen3 VL 32B Thinking | Qwen | 0.862 | 2025-09-22 | evidence |
| Qwen3 VL 4B Instruct | Qwen | 0.825 | 2025-09-22 | evidence |
| Qwen3 VL 4B Thinking | Qwen | 0.84 | 2025-09-22 | evidence |
| Qwen3 VL 8B Instruct | Qwen | 0.831 | 2025-09-22 | evidence |
| Qwen3 VL 8B Thinking | Qwen | 0.855 | 2025-09-22 | evidence |
| Qwen3-235B-A22B-Instruct-2507 | Qwen | 0.852 | 2025-07-22 | evidence |
| Qwen3-235B-A22B-Thinking-2507 | Qwen | 0.883 | 2025-07-25 | evidence |
| Qwen3-Next-80B-A3B-Instruct | Qwen | 0.873 | 2025-09-10 | evidence |
| Qwen3-Next-80B-A3B-Thinking | Qwen | 0.846 | 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.