# Memory Updating on HaluMem Medium

Source: [Memory Updating on HaluMem Medium](<https://www.sota2.com/research/sota/memory-updating-on-halumem-medium>)

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

Data updated: 2026-05-13T10:24:28.170Z

Evaluation of model performance on the HaluMem Medium subset for the Memory Updating task, reporting metrics C, H, and O.

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 | Memory Updating |
| Dataset (including any stated split) | HaluMem Medium |
| Metric | C Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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/memory-updating-on-halumem-medium.md?metric=C%20Score>): Higher is better; unit: SCALAR.

- [H Score](<https://www.sota2.com/research/sota/memory-updating-on-halumem-medium.md?metric=H%20Score>): Higher is better; unit: SCALAR.

- [O Score](<https://www.sota2.com/research/sota/memory-updating-on-halumem-medium.md?metric=O%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | C Score | Result date | Report paper |
| --- | --- | --- | --- |
| MemOS | 62.11 | Not recorded | 6a0405a8dbc836b87d82765f |
| Zep | 47.28 | Not recorded | 6a0405a8dbc836b87d82765f |
| Mem0 | 25.5 | Not recorded | 6a0405a8dbc836b87d82765f |
| SAGE | 21.67 | Not recorded | 6a0405a8dbc836b87d82765f |
| Supermemory | 16.37 | Not recorded | 6a0405a8dbc836b87d82765f |
| SAGE +1 round | 10.86 | Not recorded | 6a0405a8dbc836b87d82765f |
| SAGE | 7.34 | Not recorded | 6a0405a8dbc836b87d82765f |
| Memobase | 5.2 | Not recorded | 6a0405a8dbc836b87d82765f |

### MemOS

C Score: 62.11. Result ID: 6a044fc747f34ce924eac49e.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405a8dbc836b87d82765f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78d81e209131cea7abd9.md>)

Recorded evaluation configuration: {"Evaluation protocol":"standard"}. This record does not assert independent reproduction.

### Zep

C Score: 47.28. Result ID: 6a044fc747f34ce924eac49d.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405a8dbc836b87d82765f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76b41e209131cea6e944.md>)

Recorded evaluation configuration: {"Evaluation protocol":"standard"}. This record does not assert independent reproduction.

### Mem0

C Score: 25.5. Result ID: 6a044fc747f34ce924eac49c.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405a8dbc836b87d82765f.md>)

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

Recorded evaluation configuration: {"Evaluation protocol":"standard"}. This record does not assert independent reproduction.

### SAGE

C Score: 21.67. Result ID: 6a044fc747f34ce924eac49f.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405a8dbc836b87d82765f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0405a8dbc836b87d82765f.md>)

Recorded evaluation configuration: {"Evaluation protocol":"0-shot"}. This record does not assert independent reproduction.

### Supermemory

C Score: 16.37. Result ID: 6a044fc747f34ce924eac49b.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405a8dbc836b87d82765f.md>)

Recorded evaluation configuration: {"Evaluation protocol":"standard"}. This record does not assert independent reproduction.

### SAGE +1 round

C Score: 10.86. Result ID: 6a044fc747f34ce924eac4a1.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405a8dbc836b87d82765f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0405a8dbc836b87d82765f.md>)

Recorded evaluation configuration: {"Evaluation protocol":"trained"}. This record does not assert independent reproduction.

### SAGE

C Score: 7.34. Result ID: 6a044fc747f34ce924eac4a0.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405a8dbc836b87d82765f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0405a8dbc836b87d82765f.md>)

Recorded evaluation configuration: {"Evaluation protocol":"trained"}. This record does not assert independent reproduction.

### Memobase

C Score: 5.2. Result ID: 6a044fc747f34ce924eac49a.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405a8dbc836b87d82765f.md>)

Recorded evaluation configuration: {"Evaluation protocol":"standard"}. This record does not assert independent reproduction.

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