# Text Synthesis on C3EBENCH

Source: [Text Synthesis on C3EBENCH](<https://www.sota2.com/research/sota/text-synthesis-on-c3ebench>)

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

Data updated: 2026-03-04T10:20:43.461Z

Evaluation of models performing Text Synthesis tasks using the C3EBENCH dataset, assessed using metrics such as Cloze, Expand, Edit, and E2E scores.

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 | Text Synthesis |
| Dataset (including any stated split) | C3EBENCH |
| Metric | Cloze Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Cloze Score](<https://www.sota2.com/research/sota/text-synthesis-on-c3ebench.md?metric=Cloze%20Score>): Higher is better; unit: SCALAR.

- [Expand Score](<https://www.sota2.com/research/sota/text-synthesis-on-c3ebench.md?metric=Expand%20Score>): Higher is better; unit: SCALAR.

- [Edit Score](<https://www.sota2.com/research/sota/text-synthesis-on-c3ebench.md?metric=Edit%20Score>): Higher is better; unit: SCALAR.

- [E2E Score](<https://www.sota2.com/research/sota/text-synthesis-on-c3ebench.md?metric=E2E%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Cloze Score | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3-235B-A22B | 4.6 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| GPT-5.2-2025-11-20 | 4.53 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| Gemini-3 Pro | 4.44 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| Claude-4.5 Sonnet | 4.44 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| Grok-4 | 4.42 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| Qwen3-Max | 4.32 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| DeepSeek-v3.2 | 4.22 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| Kimi-K2-Thinking | 3.99 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| Qwen3-32B | 3.74 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| Qwen3-8B | 3.14 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| Llama-3.1-405B | 3.09 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| GLM-4.7 | 2.62 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| Llama-3.1-8B | 2.44 | Not recorded | 69a66bce2d603e6de3e3cc0a |
| Hermes-3-Llama-70B | 1.88 | Not recorded | 69a66bce2d603e6de3e3cc0a |

### Qwen3-235B-A22B

Cloze Score: 4.6. Result ID: 69a8076e6dbb7075b94d7859.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model Category":"Open Source LLMs"}. This record does not assert independent reproduction.

### GPT-5.2-2025-11-20

Cloze Score: 4.53. Result ID: 69a8076e6dbb7075b94d784e.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary LLMs"}. This record does not assert independent reproduction.

### Gemini-3 Pro

Cloze Score: 4.44. Result ID: 69a8076e6dbb7075b94d784f.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary LLMs"}. This record does not assert independent reproduction.

### Claude-4.5 Sonnet

Cloze Score: 4.44. Result ID: 69a8076e6dbb7075b94d7850.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary LLMs"}. This record does not assert independent reproduction.

### Grok-4

Cloze Score: 4.42. Result ID: 69a8076e6dbb7075b94d7851.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary LLMs"}. This record does not assert independent reproduction.

### Qwen3-Max

Cloze Score: 4.32. Result ID: 69a8076e6dbb7075b94d7853.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary LLMs"}. This record does not assert independent reproduction.

### DeepSeek-v3.2

Cloze Score: 4.22. Result ID: 69a8076e6dbb7075b94d7855.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

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

Recorded evaluation configuration: {"Model Category":"Proprietary LLMs"}. This record does not assert independent reproduction.

### Kimi-K2-Thinking

Cloze Score: 3.99. Result ID: 69a8076e6dbb7075b94d7854.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

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

Recorded evaluation configuration: {"Model Category":"Proprietary LLMs"}. This record does not assert independent reproduction.

### Qwen3-32B

Cloze Score: 3.74. Result ID: 69a8076e6dbb7075b94d785a.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model Category":"Open Source LLMs"}. This record does not assert independent reproduction.

### Qwen3-8B

Cloze Score: 3.14. Result ID: 69a8076e6dbb7075b94d785b.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model Category":"Open Source LLMs"}. This record does not assert independent reproduction.

### Llama-3.1-405B

Cloze Score: 3.09. Result ID: 69a8076e6dbb7075b94d7856.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Model Category":"Open Source LLMs"}. This record does not assert independent reproduction.

### GLM-4.7

Cloze Score: 2.62. Result ID: 69a8076e6dbb7075b94d7852.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary LLMs"}. This record does not assert independent reproduction.

### Llama-3.1-8B

Cloze Score: 2.44. Result ID: 69a8076e6dbb7075b94d7858.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Model Category":"Open Source LLMs"}. This record does not assert independent reproduction.

### Hermes-3-Llama-70B

Cloze Score: 1.88. Result ID: 69a8076e6dbb7075b94d7857.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bce2d603e6de3e3cc0a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Model Category":"Open Source LLMs"}. This record does not assert independent reproduction.

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