# General Writing on Arena-Hard Creative Writing

Source: [General Writing on Arena-Hard Creative Writing](<https://www.sota2.com/research/sota/general-writing-on-arena-hard-creative-writing>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:03:52.648Z

Evaluation of model performance on the Arena-Hard Creative Writing dataset using a general Score metric.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | General Writing |
| Dataset (including any stated split) | Arena-Hard Creative Writing |
| Metric | Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Score](<https://www.sota2.com/research/sota/general-writing-on-arena-hard-creative-writing.md?metric=Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| Gemini-3.0 Pro | 93.6 | Not recorded | 695de86653fdd5c3617439f3 |
| GPT-5 High | 92.2 | Not recorded | 695de86653fdd5c3617439f3 |
| DeepSeek-V3.2 Thinking | 88.8 | Not recorded | 695de86653fdd5c3617439f3 |
| MiMo-V2-Flash | 86.2 | Not recorded | 695de86653fdd5c3617439f3 |
| Kimi-K2 Thinking | 80.1 | Not recorded | 695de86653fdd5c3617439f3 |
| Claude Sonnet 4.5 | 76.7 | Not recorded | 695de86653fdd5c3617439f3 |

### Gemini-3.0 Pro

Score: 93.6. Result ID: 6996a26a5698665ec4ebf1ab.

[Reporting paper](<https://www.sota2.com/research/paper/695de86653fdd5c3617439f3.md>)

Recorded evaluation configuration: {"Variant":"Pro"}. This record does not assert independent reproduction.

### GPT-5 High

Score: 92.2. Result ID: 6996a26a5698665ec4ebf1ad.

[Reporting paper](<https://www.sota2.com/research/paper/695de86653fdd5c3617439f3.md>)

Recorded evaluation configuration: {"Variant":"High"}. This record does not assert independent reproduction.

### DeepSeek-V3.2 Thinking

Score: 88.8. Result ID: 6996a26a5698665ec4ebf1aa.

[Reporting paper](<https://www.sota2.com/research/paper/695de86653fdd5c3617439f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692fc410d6b0dd33429332f4.md>)

Recorded evaluation configuration: {"Thinking Mode":true}. This record does not assert independent reproduction.

### MiMo-V2-Flash

Score: 86.2. Result ID: 6996a26a5698665ec4ebf1a8.

[Reporting paper](<https://www.sota2.com/research/paper/695de86653fdd5c3617439f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86653fdd5c3617439f3.md>)

[Implementation](<https://github.com/XiaomiMiMo/MiMo-V2-Flash>)

Recorded evaluation configuration: {"Variant":"Flash"}. This record does not assert independent reproduction.

### Kimi-K2 Thinking

Score: 80.1. Result ID: 6996a26a5698665ec4ebf1a9.

[Reporting paper](<https://www.sota2.com/research/paper/695de86653fdd5c3617439f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a1.md>)

Recorded evaluation configuration: {"Thinking Mode":true}. This record does not assert independent reproduction.

### Claude Sonnet 4.5

Score: 76.7. Result ID: 6996a26a5698665ec4ebf1ac.

[Reporting paper](<https://www.sota2.com/research/paper/695de86653fdd5c3617439f3.md>)

Recorded evaluation configuration: {"Variant":"Sonnet 4.5"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.