# Long-context Question Answering on L-Eval

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

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

Data updated: 2026-03-23T11:14:20.040Z

Evaluation of model performance on the L-Eval dataset for Long-context Question Answering, reporting scores for Coursera QA, QuALITY, SFictionQA, TPO, LongFQA, Legal Contract QA, and overall Average.

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) | L-Eval |
| Metric | Coursera QA |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

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

- [QuALITY](<https://www.sota2.com/research/sota/long-context-question-answering-on-l-eval.md?metric=QuALITY>): Higher is better; unit: PERCENT.

- [SFictionQA](<https://www.sota2.com/research/sota/long-context-question-answering-on-l-eval.md?metric=SFictionQA>): Higher is better; unit: PERCENT.

- [TPO](<https://www.sota2.com/research/sota/long-context-question-answering-on-l-eval.md?metric=TPO>): Higher is better; unit: PERCENT.

- [LongFQA](<https://www.sota2.com/research/sota/long-context-question-answering-on-l-eval.md?metric=LongFQA>): Higher is better; unit: PERCENT.

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

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

## Recorded results

| Method | Coursera QA | Result date | Report paper |
| --- | --- | --- | --- |
| LongLLMLingua | 30.2 | Not recorded | 69c0c8d70636e5bf4afc394a |
| BEAVER | 28.3 | Not recorded | 69c0c8d70636e5bf4afc394a |
| LLMLingua-2 | 25.3 | Not recorded | 69c0c8d70636e5bf4afc394a |
| LLMLingua | 24.9 | Not recorded | 69c0c8d70636e5bf4afc394a |

### LongLLMLingua

Coursera QA: 30.2. Result ID: 69c1208247f34ce924a97e50.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8d70636e5bf4afc394a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74701e209131cea61c6d.md>)

[Implementation](<https://aka.ms/LLMLingua>)

Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Input budget constraint":"2,000-token","Tokens":"2,196","1/τ":"4×"}. This record does not assert independent reproduction.

### BEAVER

Coursera QA: 28.3. Result ID: 69c1208247f34ce924a97e52.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8d70636e5bf4afc394a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c0c8d70636e5bf4afc394a.md>)

[Implementation](<https://github.com/JusperLee/BEAVER>)

Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Input budget constraint":"2,000-token","Tokens":"2,180","1/τ":"4×"}. This record does not assert independent reproduction.

### LLMLingua-2

Coursera QA: 25.3. Result ID: 69c1208247f34ce924a97e51.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8d70636e5bf4afc394a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74701e209131cea61cb2.md>)

[Implementation](<https://aka.ms/LLMLingua-2>)

Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Input budget constraint":"2,000-token","Tokens":"2,110","1/τ":"4×"}. This record does not assert independent reproduction.

### LLMLingua

Coursera QA: 24.9. Result ID: 69c1208247f34ce924a97e4f.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8d70636e5bf4afc394a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71621e209131cea5103a.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Input budget constraint":"2,000-token","Tokens":"2,122","1/τ":"4×"}. This record does not assert independent reproduction.

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