# Long-context Memory Management on LoCoMo (test)

Source: [Long-context Memory Management on LoCoMo (test)](<https://www.sota2.com/research/sota/long-context-memory-management-on-locomo-test>)

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

Data updated: 2026-03-23T11:38:04.441Z

Evaluation of model performance on the LoCoMo test set focusing on long-context memory management, specifically measuring token overhead, computational cost, and memory footprint.

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 Management |
| Dataset (including any stated split) | LoCoMo (test) |
| Metric | Added Tokens (mean) |
| Unit | SCALAR |
| Direction | Lower 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

- [Added Tokens (mean)](<https://www.sota2.com/research/sota/long-context-memory-management-on-locomo-test.md?metric=Added%20Tokens%20(mean)>): Lower is better; unit: SCALAR.

- [Context Cost ($)](<https://www.sota2.com/research/sota/long-context-memory-management-on-locomo-test.md?metric=Context%20Cost%20(%24)>): Lower is better; unit: OTHER.

- [Context Footprint (%)](<https://www.sota2.com/research/sota/long-context-memory-management-on-locomo-test.md?metric=Context%20Footprint%20(%25)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Added Tokens (mean) | Result date | Report paper |
| --- | --- | --- | --- |
| Memori | 1294 | Not recorded | 69c0c8ea0636e5bf4afc3a76 |
| Mem0 | 1764 | Not recorded | 69c0c8ea0636e5bf4afc3a76 |
| Zep | 3911 | Not recorded | 69c0c8ea0636e5bf4afc3a76 |
| Full-Context | 26031 | Not recorded | 69c0c8ea0636e5bf4afc3a76 |

### Memori

Added Tokens (mean): 1294. Result ID: 69c1261147f34ce924a9af9f.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8ea0636e5bf4afc3a76.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c0c8ea0636e5bf4afc3a76.md>)

Recorded evaluation configuration: {"pricing\_model":"gpt-4o-mini ($0.8 per 1M tokens)"}. This record does not assert independent reproduction.

### Mem0

Added Tokens (mean): 1764. Result ID: 69c1261147f34ce924a9afa1.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8ea0636e5bf4afc3a76.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa784b1e209131cea77ad6.md>)

Recorded evaluation configuration: {"pricing\_model":"gpt-4o-mini ($0.8 per 1M tokens)"}. This record does not assert independent reproduction.

### Zep

Added Tokens (mean): 3911. Result ID: 69c1261147f34ce924a9afa2.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8ea0636e5bf4afc3a76.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa784b1e209131cea77ad6.md>)

Recorded evaluation configuration: {"pricing\_model":"gpt-4o-mini ($0.8 per 1M tokens)"}. This record does not assert independent reproduction.

### Full-Context

Added Tokens (mean): 26031. Result ID: 69c1261147f34ce924a9afa0.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8ea0636e5bf4afc3a76.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa784b1e209131cea77ad6.md>)

Recorded evaluation configuration: {"pricing\_model":"gpt-4o-mini ($0.8 per 1M tokens)"}. This record does not assert independent reproduction.

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