# Human move prediction on bullet decision points 12,000 balanced (Elo 2700+)

Source: [Human move prediction on bullet decision points 12,000 balanced (Elo 2700+)](<https://www.sota2.com/research/sota/human-move-prediction-on-bullet-decision-points-12-000-balanced-elo-2700-plus>)

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

Data updated: 2026-04-01T08:42:42.137Z

Evaluation of model performance on predicting human moves using the subset of the '12,000 balanced bullet decision points' dataset specifically filtered for Elo ratings of 2700 and above, typically measured by Top-1 accuracy.

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 | Human move prediction |
| Dataset (including any stated split) | bullet decision points 12,000 balanced (Elo 2700+) |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/human-move-prediction-on-bullet-decision-points-12-000-balanced-elo-2700-plus.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| V2.2 final | 0.568 | Not recorded | 69cca69e0636e5bf4afcbc11 |
| Maia-2 blitz | 0.504 | Not recorded | 69cca69e0636e5bf4afcbc11 |
| Maia-2 rapid | 0.5 | Not recorded | 69cca69e0636e5bf4afcbc11 |

### V2.2 final

Top-1 Accuracy: 0.568. Result ID: 69ccda4147f34ce924b6997c.

[Reporting paper](<https://www.sota2.com/research/paper/69cca69e0636e5bf4afcbc11.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cca69e0636e5bf4afcbc11.md>)

Recorded evaluation configuration: {"Input format":"full preceding move sequence"}. This record does not assert independent reproduction.

### Maia-2 blitz

Top-1 Accuracy: 0.504. Result ID: 69ccda4147f34ce924b6997e.

[Reporting paper](<https://www.sota2.com/research/paper/69cca69e0636e5bf4afcbc11.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75751e209131cea68118.md>)

Recorded evaluation configuration: {"Input format":"FEN string"}. This record does not assert independent reproduction.

### Maia-2 rapid

Top-1 Accuracy: 0.5. Result ID: 69ccda4147f34ce924b6997d.

[Reporting paper](<https://www.sota2.com/research/paper/69cca69e0636e5bf4afcbc11.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75751e209131cea68118.md>)

Recorded evaluation configuration: {"Input format":"FEN string"}. This record does not assert independent reproduction.

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