# Long-context Memory Evaluation on LongMemEval v0.6.0 (strict)

Source: [Long-context Memory Evaluation on LongMemEval v0.6.0 (strict)](<https://www.sota2.com/research/sota/long-context-memory-evaluation-on-longmemeval-v0-6-0-strict>)

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

Data updated: 2026-05-07T09:23:02.115Z

Evaluation of model performance on the strict v0.6.0 version of the LongMemEval dataset, assessing long-context memory capabilities using metrics like Accuracy and Correct counts.

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) | LongMemEval v0.6.0 (strict) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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-longmemeval-v0-6-0-strict.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Accuracy 95% CI (Lower Bound)](<https://www.sota2.com/research/sota/long-context-memory-evaluation-on-longmemeval-v0-6-0-strict.md?metric=Accuracy%2095%25%20CI%20(Lower%20Bound)>): Higher is better; unit: PERCENT.

- [Correct Count](<https://www.sota2.com/research/sota/long-context-memory-evaluation-on-longmemeval-v0-6-0-strict.md?metric=Correct%20Count>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| TM Pro | 92 | Not recorded | 69fc1c8d5497b3b670c884f7 |
| TM Pro | 87.8 | Not recorded | 69fc1c8d5497b3b670c884f7 |
| RAG | 87 | Not recorded | 69fc1c8d5497b3b670c884f7 |
| EverMemOS | 83 | Not recorded | 69fc1c8d5497b3b670c884f7 |
| Engram | 82.2 | Not recorded | 69fc1c8d5497b3b670c884f7 |
| BM25 | 81.6 | Not recorded | 69fc1c8d5497b3b670c884f7 |
| Mem0 | 66 | Not recorded | 69fc1c8d5497b3b670c884f7 |

### TM Pro

Accuracy: 92. Result ID: 69fc59e047f34ce924df58b3.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c8d5497b3b670c884f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1c8d5497b3b670c884f7.md>)

Recorded evaluation configuration: {"Variant":"oracle","Answer model":"gpt-4.1-mini"}. This record does not assert independent reproduction.

### TM Pro

Accuracy: 87.8. Result ID: 69fc59e047f34ce924df58b4.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c8d5497b3b670c884f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1c8d5497b3b670c884f7.md>)

Recorded evaluation configuration: {"Variant":"3-run mean, strict","Answer model":"gpt-4.1-mini"}. This record does not assert independent reproduction.

### RAG

Accuracy: 87. Result ID: 69fc59e047f34ce924df58b5.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c8d5497b3b670c884f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b91e209131cea23c26.md>)

[Implementation](<https://github.com/huggingface/transformers/blob/master/examples/rag/>)

Recorded evaluation configuration: {"Backbone":"ChromaDB","Answer model":"gpt-4.1-mini"}. This record does not assert independent reproduction.

### EverMemOS

Accuracy: 83. Result ID: 69fc59e047f34ce924df58b6.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c8d5497b3b670c884f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695c970453fdd5c36174372b.md>)

Recorded evaluation configuration: {"Answer model":"gpt-4o"}. This record does not assert independent reproduction.

### Engram

Accuracy: 82.2. Result ID: 69fc59e047f34ce924df58b7.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c8d5497b3b670c884f7.md>)

Recorded evaluation configuration: {"Answer model":"gpt-4.1-mini"}. This record does not assert independent reproduction.

### BM25

Accuracy: 81.6. Result ID: 69fc59e047f34ce924df58b8.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c8d5497b3b670c884f7.md>)

Recorded evaluation configuration: {"Answer model":"gpt-4.1-mini"}. This record does not assert independent reproduction.

### Mem0

Accuracy: 66. Result ID: 69fc59e047f34ce924df58b9.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c8d5497b3b670c884f7.md>)

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

Recorded evaluation configuration: {"Answer model":"gpt-4.1-mini"}. This record does not assert independent reproduction.

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