# Long-context Memory Evaluation on BEHEMOTH LongMemEval (out-of-distribution)

Source: [Long-context Memory Evaluation on BEHEMOTH LongMemEval (out-of-distribution)](<https://www.sota2.com/research/sota/long-context-memory-evaluation-on-behemoth-longmemeval-out-of-distribution>)

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

Data updated: 2026-04-14T12:22:17.465Z

Evaluation of model performance on the out-of-distribution subset of the BEHEMOTH LongMemEval dataset, focusing on long-context memory capabilities, typically measured by Accuracy.

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 Memory Evaluation |
| Dataset (including any stated split) | BEHEMOTH LongMemEval (out-of-distribution) |
| Metric | Accuracy |
| Unit | PERCENT |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/long-context-memory-evaluation-on-behemoth-longmemeval-out-of-distribution.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CluE | 63.07 | Not recorded | 69ddca7c7d0172140ec79f89 |
| MemEvolve | 56.82 | Not recorded | 69ddca7c7d0172140ec79f89 |
| Simple | 46.02 | Not recorded | 69ddca7c7d0172140ec79f89 |
| GEPA | 35.06 | Not recorded | 69ddca7c7d0172140ec79f89 |
| ACE | 29.71 | Not recorded | 69ddca7c7d0172140ec79f89 |
| No Memory | 20.45 | Not recorded | 69ddca7c7d0172140ec79f89 |

### CluE

Accuracy: 63.07. Result ID: 69de316747f34ce924c6fda0.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca7c7d0172140ec79f89.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca7c7d0172140ec79f89.md>)

[Implementation](<https://github.com/ayyyq/heterogeneous-memory-extraction>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MemEvolve

Accuracy: 56.82. Result ID: 69de316747f34ce924c6fd9f.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca7c7d0172140ec79f89.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Simple

Accuracy: 46.02. Result ID: 69de316747f34ce924c6fd9c.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca7c7d0172140ec79f89.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GEPA

Accuracy: 35.06. Result ID: 69de316747f34ce924c6fd9d.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca7c7d0172140ec79f89.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a3a1e209131cea81ee3.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ACE

Accuracy: 29.71. Result ID: 69de316747f34ce924c6fd9e.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca7c7d0172140ec79f89.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8afd2.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### No Memory

Accuracy: 20.45. Result ID: 69de316747f34ce924c6fd9b.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca7c7d0172140ec79f89.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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