# Evidence-round recall on LongMemEval 100 question sample

Source: [Evidence-round recall on LongMemEval 100 question sample](<https://www.sota2.com/research/sota/evidence-round-recall-on-longmemeval-100-question-sample>)

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

Data updated: 2026-06-19T08:15:07.116Z

Evaluation of model performance on evidence-round recall using the 100-question sample subset of the LongMemEval dataset.

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 | Evidence-round recall |
| Dataset (including any stated split) | LongMemEval 100 question sample |
| Metric | Evidence-round Recall |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 48 of 48 |
| 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

- [Evidence-round Recall](<https://www.sota2.com/research/sota/evidence-round-recall-on-longmemeval-100-question-sample.md?metric=Evidence-round%20Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Evidence-round Recall | Result date | Report paper |
| --- | --- | --- | --- |
| lc-mmr | 100 | Not recorded | 6a34cd47206542251d7c613b |
| PACMS | 100 | Not recorded | 6a34cd47206542251d7c613b |
| lc-mmr | 99.9 | Not recorded | 6a34cd47206542251d7c613b |
| PACMS | 99.9 | Not recorded | 6a34cd47206542251d7c613b |
| lc-mmr | 99.4 | Not recorded | 6a34cd47206542251d7c613b |
| lc-mmr | 99.3 | Not recorded | 6a34cd47206542251d7c613b |
| PACMS | 99.1 | Not recorded | 6a34cd47206542251d7c613b |
| top-k | 98.2 | Not recorded | 6a34cd47206542251d7c613b |
| top-k | 98.2 | Not recorded | 6a34cd47206542251d7c613b |
| top-k | 97.8 | Not recorded | 6a34cd47206542251d7c613b |
| top-k | 97.4 | Not recorded | 6a34cd47206542251d7c613b |
| PACMS | 97.2 | Not recorded | 6a34cd47206542251d7c613b |
| lc-mmr | 96.6 | Not recorded | 6a34cd47206542251d7c613b |
| PACMS | 95.2 | Not recorded | 6a34cd47206542251d7c613b |
| top-k | 94 | Not recorded | 6a34cd47206542251d7c613b |
| PACMS | 94 | Not recorded | 6a34cd47206542251d7c613b |
| top-k | 93.8 | Not recorded | 6a34cd47206542251d7c613b |
| top-k | 93.3 | Not recorded | 6a34cd47206542251d7c613b |
| top-k | 92.8 | Not recorded | 6a34cd47206542251d7c613b |
| lc-mmr | 92.2 | Not recorded | 6a34cd47206542251d7c613b |
| PACMS | 90.9 | Not recorded | 6a34cd47206542251d7c613b |
| lc-mmr | 89.5 | Not recorded | 6a34cd47206542251d7c613b |
| PACMS | 86 | Not recorded | 6a34cd47206542251d7c613b |
| lc-mmr | 83.6 | Not recorded | 6a34cd47206542251d7c613b |
| top-k | 81.7 | Not recorded | 6a34cd47206542251d7c613b |
| top-k | 80.8 | Not recorded | 6a34cd47206542251d7c613b |
| PACMS | 80.4 | Not recorded | 6a34cd47206542251d7c613b |
| top-k | 80 | Not recorded | 6a34cd47206542251d7c613b |
| top-k | 79 | Not recorded | 6a34cd47206542251d7c613b |
| PACMS | 76 | Not recorded | 6a34cd47206542251d7c613b |
| last-k | 74.4 | Not recorded | 6a34cd47206542251d7c613b |
| lc-mmr | 74.3 | Not recorded | 6a34cd47206542251d7c613b |
| PACMS | 73.7 | Not recorded | 6a34cd47206542251d7c613b |
| PACMS | 70.4 | Not recorded | 6a34cd47206542251d7c613b |
| lc-mmr | 66.8 | Not recorded | 6a34cd47206542251d7c613b |
| last-k | 62 | Not recorded | 6a34cd47206542251d7c613b |
| lc-mmr | 55.2 | Not recorded | 6a34cd47206542251d7c613b |
| last-k | 52.1 | Not recorded | 6a34cd47206542251d7c613b |
| last-k | 48.9 | Not recorded | 6a34cd47206542251d7c613b |
| lc-mmr | 42.1 | Not recorded | 6a34cd47206542251d7c613b |
| last-k | 23.8 | Not recorded | 6a34cd47206542251d7c613b |
| last-k | 22.1 | Not recorded | 6a34cd47206542251d7c613b |
| last-k | 13.9 | Not recorded | 6a34cd47206542251d7c613b |
| last-k | 0.3 | Not recorded | 6a34cd47206542251d7c613b |
| last-k | 0.3 | Not recorded | 6a34cd47206542251d7c613b |
| last-k | 0.1 | Not recorded | 6a34cd47206542251d7c613b |
| last-k | 0 | Not recorded | 6a34cd47206542251d7c613b |
| last-k | 0 | Not recorded | 6a34cd47206542251d7c613b |

### lc-mmr

Evidence-round Recall: 100. Result ID: 6a34fa83fbc373592c324218.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"8"}. This record does not assert independent reproduction.

### PACMS

Evidence-round Recall: 100. Result ID: 6a34fa83fbc373592c32421a.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"8"}. This record does not assert independent reproduction.

### lc-mmr

Evidence-round Recall: 99.9. Result ID: 6a34fa83fbc373592c324214.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"4"}. This record does not assert independent reproduction.

### PACMS

Evidence-round Recall: 99.9. Result ID: 6a34fa83fbc373592c324216.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"4"}. This record does not assert independent reproduction.

### lc-mmr

Evidence-round Recall: 99.4. Result ID: 6a34fa83fbc373592c324208.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"8"}. This record does not assert independent reproduction.

### lc-mmr

Evidence-round Recall: 99.3. Result ID: 6a34fa83fbc373592c324210.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"2"}. This record does not assert independent reproduction.

### PACMS

Evidence-round Recall: 99.1. Result ID: 6a34fa83fbc373592c324212.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"2"}. This record does not assert independent reproduction.

### top-k

Evidence-round Recall: 98.2. Result ID: 6a34fa83fbc373592c324213.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"4"}. This record does not assert independent reproduction.

### top-k

Evidence-round Recall: 98.2. Result ID: 6a34fa83fbc373592c324217.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"8"}. This record does not assert independent reproduction.

### top-k

Evidence-round Recall: 97.8. Result ID: 6a34fa83fbc373592c32420f.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"2"}. This record does not assert independent reproduction.

### top-k

Evidence-round Recall: 97.4. Result ID: 6a34fa83fbc373592c32420b.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"0"}. This record does not assert independent reproduction.

### PACMS

Evidence-round Recall: 97.2. Result ID: 6a34fa83fbc373592c32420a.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"8"}. This record does not assert independent reproduction.

### lc-mmr

Evidence-round Recall: 96.6. Result ID: 6a34fa83fbc373592c324204.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"4"}. This record does not assert independent reproduction.

### PACMS

Evidence-round Recall: 95.2. Result ID: 6a34fa83fbc373592c324206.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"4"}. This record does not assert independent reproduction.

### top-k

Evidence-round Recall: 94. Result ID: 6a34fa83fbc373592c324207.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"8"}. This record does not assert independent reproduction.

### PACMS

Evidence-round Recall: 94. Result ID: 6a34fa83fbc373592c32420e.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"0"}. This record does not assert independent reproduction.

### top-k

Evidence-round Recall: 93.8. Result ID: 6a34fa83fbc373592c324203.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"4"}. This record does not assert independent reproduction.

### top-k

Evidence-round Recall: 93.3. Result ID: 6a34fa83fbc373592c3241ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"2"}. This record does not assert independent reproduction.

### top-k

Evidence-round Recall: 92.8. Result ID: 6a34fa83fbc373592c3241fb.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"0"}. This record does not assert independent reproduction.

### lc-mmr

Evidence-round Recall: 92.2. Result ID: 6a34fa83fbc373592c32420c.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"0"}. This record does not assert independent reproduction.

### PACMS

Evidence-round Recall: 90.9. Result ID: 6a34fa83fbc373592c324202.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"2"}. This record does not assert independent reproduction.

### lc-mmr

Evidence-round Recall: 89.5. Result ID: 6a34fa83fbc373592c324200.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"2"}. This record does not assert independent reproduction.

### PACMS

Evidence-round Recall: 86. Result ID: 6a34fa83fbc373592c3241fe.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"0"}. This record does not assert independent reproduction.

### lc-mmr

Evidence-round Recall: 83.6. Result ID: 6a34fa83fbc373592c3241f8.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"8"}. This record does not assert independent reproduction.

### top-k

Evidence-round Recall: 81.7. Result ID: 6a34fa83fbc373592c3241f7.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"8"}. This record does not assert independent reproduction.

### top-k

Evidence-round Recall: 80.8. Result ID: 6a34fa83fbc373592c3241f3.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"4"}. This record does not assert independent reproduction.

### PACMS

Evidence-round Recall: 80.4. Result ID: 6a34fa83fbc373592c3241fa.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"8"}. This record does not assert independent reproduction.

### top-k

Evidence-round Recall: 80. Result ID: 6a34fa83fbc373592c3241ef.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"2"}. This record does not assert independent reproduction.

### top-k

Evidence-round Recall: 79. Result ID: 6a34fa83fbc373592c3241eb.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"0"}. This record does not assert independent reproduction.

### PACMS

Evidence-round Recall: 76. Result ID: 6a34fa83fbc373592c3241f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"4"}. This record does not assert independent reproduction.

### last-k

Evidence-round Recall: 74.4. Result ID: 6a34fa83fbc373592c32420d.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"0"}. This record does not assert independent reproduction.

### lc-mmr

Evidence-round Recall: 74.3. Result ID: 6a34fa83fbc373592c3241fc.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"0"}. This record does not assert independent reproduction.

### PACMS

Evidence-round Recall: 73.7. Result ID: 6a34fa83fbc373592c3241f2.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"2"}. This record does not assert independent reproduction.

### PACMS

Evidence-round Recall: 70.4. Result ID: 6a34fa83fbc373592c3241ee.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"0"}. This record does not assert independent reproduction.

### lc-mmr

Evidence-round Recall: 66.8. Result ID: 6a34fa83fbc373592c3241f4.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"4","Lambda (λ)":"0.5"}. This record does not assert independent reproduction.

### last-k

Evidence-round Recall: 62. Result ID: 6a34fa83fbc373592c324211.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"2"}. This record does not assert independent reproduction.

### lc-mmr

Evidence-round Recall: 55.2. Result ID: 6a34fa83fbc373592c3241f0.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"2","Lambda (λ)":"0.5"}. This record does not assert independent reproduction.

### last-k

Evidence-round Recall: 52.1. Result ID: 6a34fa83fbc373592c3241fd.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"0"}. This record does not assert independent reproduction.

### last-k

Evidence-round Recall: 48.9. Result ID: 6a34fa83fbc373592c324215.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"4"}. This record does not assert independent reproduction.

### lc-mmr

Evidence-round Recall: 42.1. Result ID: 6a34fa83fbc373592c3241ec.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"0","Lambda (λ)":"0.5"}. This record does not assert independent reproduction.

### last-k

Evidence-round Recall: 23.8. Result ID: 6a34fa83fbc373592c3241ed.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"0"}. This record does not assert independent reproduction.

### last-k

Evidence-round Recall: 22.1. Result ID: 6a34fa83fbc373592c324201.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"2"}. This record does not assert independent reproduction.

### last-k

Evidence-round Recall: 13.9. Result ID: 6a34fa83fbc373592c324219.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"70%","Redundancy level (R)":"8"}. This record does not assert independent reproduction.

### last-k

Evidence-round Recall: 0.3. Result ID: 6a34fa83fbc373592c324205.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"4"}. This record does not assert independent reproduction.

### last-k

Evidence-round Recall: 0.3. Result ID: 6a34fa83fbc373592c324209.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"45%","Redundancy level (R)":"8"}. This record does not assert independent reproduction.

### last-k

Evidence-round Recall: 0.1. Result ID: 6a34fa83fbc373592c3241f9.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"8"}. This record does not assert independent reproduction.

### last-k

Evidence-round Recall: 0. Result ID: 6a34fa83fbc373592c3241f1.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"2"}. This record does not assert independent reproduction.

### last-k

Evidence-round Recall: 0. Result ID: 6a34fa83fbc373592c3241f5.

[Reporting paper](<https://www.sota2.com/research/paper/6a34cd47206542251d7c613b.md>)

Recorded evaluation configuration: {"Budget":"20%","Redundancy level (R)":"4"}. This record does not assert independent reproduction.

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