# Multi-agent aggregation on 42-task multi-agent evaluation set

Source: [Multi-agent aggregation on 42-task multi-agent evaluation set](<https://www.sota2.com/research/sota/multi-agent-aggregation-on-42-task-multi-agent-evaluation-set>)

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

Data updated: 2026-03-24T12:54:43.579Z

Evaluation of model performance on multi-agent aggregation tasks using the 42-task evaluation set, reporting metrics such as BT-WR.

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 | Multi-agent aggregation |
| Dataset (including any stated split) | 42-task multi-agent evaluation set |
| Metric | BT-WR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [BT-WR](<https://www.sota2.com/research/sota/multi-agent-aggregation-on-42-task-multi-agent-evaluation-set.md?metric=BT-WR>): Higher is better; unit: PERCENT.

- [95% CI (BT-WR)](<https://www.sota2.com/research/sota/multi-agent-aggregation-on-42-task-multi-agent-evaluation-set.md?metric=95%25%20CI%20(BT-WR)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | BT-WR | Result date | Report paper |
| --- | --- | --- | --- |
| div\_mixed+judge | 92.9 | Not recorded | 69c21a880636e5bf4afc4820 |
| div\_strong+judge | 81 | Not recorded | 69c21a880636e5bf4afc4820 |
| homo\_opus+judge | 51.2 | Not recorded | 69c21a880636e5bf4afc4820 |
| div\_strong+vote | 49.6 | Not recorded | 69c21a880636e5bf4afc4820 |
| div\_strong+synth | 17.9 | Not recorded | 69c21a880636e5bf4afc4820 |

### div\_mixed+judge

BT-WR: 92.9. Result ID: 69c2888147f34ce924aa995e.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a880636e5bf4afc4820.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21a880636e5bf4afc4820.md>)

Recorded evaluation configuration: {"Rel. Cost":"1.0×","Exploratory":"true"}. This record does not assert independent reproduction.

### div\_strong+judge

BT-WR: 81. Result ID: 69c2888147f34ce924aa995f.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a880636e5bf4afc4820.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21a880636e5bf4afc4820.md>)

Recorded evaluation configuration: {"Rel. Cost":"2.5×"}. This record does not assert independent reproduction.

### homo\_opus+judge

BT-WR: 51.2. Result ID: 69c2888147f34ce924aa9960.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a880636e5bf4afc4820.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21a880636e5bf4afc4820.md>)

Recorded evaluation configuration: {"Rel. Cost":"2.0×"}. This record does not assert independent reproduction.

### div\_strong+vote

BT-WR: 49.6. Result ID: 69c2888147f34ce924aa9961.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a880636e5bf4afc4820.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21a880636e5bf4afc4820.md>)

Recorded evaluation configuration: {"Rel. Cost":"1.9×"}. This record does not assert independent reproduction.

### div\_strong+synth

BT-WR: 17.9. Result ID: 69c2888147f34ce924aa9962.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a880636e5bf4afc4820.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21a880636e5bf4afc4820.md>)

Recorded evaluation configuration: {"Rel. Cost":"1.9×"}. This record does not assert independent reproduction.

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