# Long-context Question Answering on Dureader

Source: [Long-context Question Answering on Dureader](<https://www.sota2.com/research/sota/long-context-question-answering-on-dureader>)

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

Data updated: 2026-02-26T05:37:57.940Z

Evaluation of model performance on the Dureader dataset for Long-context Question Answering, measured using metrics C, CLQA, and CR.

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 | Long-context Question Answering |
| Dataset (including any stated split) | Dureader |
| Metric | C Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [C Score](<https://www.sota2.com/research/sota/long-context-question-answering-on-dureader.md?metric=C%20Score>): Higher is better; unit: PERCENT.

- [CLQA Score](<https://www.sota2.com/research/sota/long-context-question-answering-on-dureader.md?metric=CLQA%20Score>): Higher is better; unit: PERCENT.

- [CR Score](<https://www.sota2.com/research/sota/long-context-question-answering-on-dureader.md?metric=CR%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | C Score | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4o | 81 | Not recorded | 68fa74bf1e209131cea637a4 |
| Mistral-Large-Instruct | 79 | Not recorded | 68fa74bf1e209131cea637a4 |
| GLM-4 | 76 | Not recorded | 68fa74bf1e209131cea637a4 |
| Claude-3-sonnet | 75.8 | Not recorded | 68fa74bf1e209131cea637a4 |
| LongCite-9B | 69 | Not recorded | 68fa74bf1e209131cea637a4 |
| LongCite-8B | 68.5 | Not recorded | 68fa74bf1e209131cea637a4 |
| GLM-4-9B-chat | 49.3 | Not recorded | 68fa74bf1e209131cea637a4 |
| Llama-3.1-70B-Instruct | 43.3 | Not recorded | 68fa74bf1e209131cea637a4 |
| Llama-3.1-8B-Instruct | 29.8 | Not recorded | 68fa74bf1e209131cea637a4 |

### GPT-4o

C Score: 81. Result ID: 699365d53a6c31484915a52f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea637a4.md>)

Recorded evaluation configuration: {"Citation Strategy":"LAC-S"}. This record does not assert independent reproduction.

### Mistral-Large-Instruct

C Score: 79. Result ID: 699365d53a6c31484915a535.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea637a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d61e209131cea4d909.md>)

[Implementation](<https://github.com/mistralai/mistral-src>)

Recorded evaluation configuration: {"Citation Strategy":"LAC-S"}. This record does not assert independent reproduction.

### GLM-4

C Score: 76. Result ID: 699365d53a6c31484915a531.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea637a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74521e209131cea610b6.md>)

Recorded evaluation configuration: {"Citation Strategy":"LAC-S"}. This record does not assert independent reproduction.

### Claude-3-sonnet

C Score: 75.8. Result ID: 699365d53a6c31484915a530.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea637a4.md>)

Recorded evaluation configuration: {"Citation Strategy":"LAC-S"}. This record does not assert independent reproduction.

### LongCite-9B

C Score: 69. Result ID: 699365d53a6c31484915a537.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea637a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea637a4.md>)

[Implementation](<https://github.com/THUDM/LongCite>)

Recorded evaluation configuration: {"Citation Strategy":"LAC-S"}. This record does not assert independent reproduction.

### LongCite-8B

C Score: 68.5. Result ID: 699365d53a6c31484915a536.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea637a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea637a4.md>)

[Implementation](<https://github.com/THUDM/LongCite>)

Recorded evaluation configuration: {"Citation Strategy":"LAC-S"}. This record does not assert independent reproduction.

### GLM-4-9B-chat

C Score: 49.3. Result ID: 699365d53a6c31484915a532.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea637a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74521e209131cea610b6.md>)

Recorded evaluation configuration: {"Citation Strategy":"LAC-S"}. This record does not assert independent reproduction.

### Llama-3.1-70B-Instruct

C Score: 43.3. Result ID: 699365d53a6c31484915a534.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea637a4.md>)

Recorded evaluation configuration: {"Citation Strategy":"LAC-S"}. This record does not assert independent reproduction.

### Llama-3.1-8B-Instruct

C Score: 29.8. Result ID: 699365d53a6c31484915a533.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea637a4.md>)

Recorded evaluation configuration: {"Citation Strategy":"LAC-S"}. This record does not assert independent reproduction.

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