# Sudoku Solving on Sudoku n=2 4x4 (eval)

Source: [Sudoku Solving on Sudoku n=2 4x4 (eval)](<https://www.sota2.com/research/sota/sudoku-solving-on-sudoku-n-2-4x4-eval>)

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

Data updated: 2026-07-02T09:44:01.110Z

Evaluation of model performance on solving 4x4 Sudoku puzzles with configuration n=2, using the evaluation set, measured by accuracy and average latency.

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 | Sudoku Solving |
| Dataset (including any stated split) | Sudoku n=2 4x4 (eval) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/sudoku-solving-on-sudoku-n-2-4x4-eval.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Average Latency (s)](<https://www.sota2.com/research/sota/sudoku-solving-on-sudoku-n-2-4x4-eval.md?metric=Average%20Latency%20(s)>): Lower is better; unit: TIME.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MPLM | 100 | Not recorded | 6a45f096dc71372d7795a3bf |
| FJ | 100 | Not recorded | 6a45f096dc71372d7795a3bf |
| GPT-5 Pro | 100 | Not recorded | 6a45f096dc71372d7795a3bf |
| Serial | 99 | Not recorded | 6a45f096dc71372d7795a3bf |
| DeepSeek R1 | 90 | Not recorded | 6a45f096dc71372d7795a3bf |

### MPLM

Accuracy: 100. Result ID: 6a4632dd60b88bb339864c9e.

[Reporting paper](<https://www.sota2.com/research/paper/6a45f096dc71372d7795a3bf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a45f096dc71372d7795a3bf.md>)

Recorded evaluation configuration: {"Reasoning Paradigm":"Message Passing"}. This record does not assert independent reproduction.

### FJ

Accuracy: 100. Result ID: 6a4632dd60b88bb339864c9f.

[Reporting paper](<https://www.sota2.com/research/paper/6a45f096dc71372d7795a3bf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aa41e209131cea8451b.md>)

Recorded evaluation configuration: {"Reasoning Paradigm":"Fork-Join"}. This record does not assert independent reproduction.

### GPT-5 Pro

Accuracy: 100. Result ID: 6a4632dd60b88bb339864ca2.

[Reporting paper](<https://www.sota2.com/research/paper/6a45f096dc71372d7795a3bf.md>)

Recorded evaluation configuration: {"queries":"20","API":"batched"}. This record does not assert independent reproduction.

### Serial

Accuracy: 99. Result ID: 6a4632dd60b88bb339864ca0.

[Reporting paper](<https://www.sota2.com/research/paper/6a45f096dc71372d7795a3bf.md>)

Recorded evaluation configuration: {"Reasoning Paradigm":"Serial"}. This record does not assert independent reproduction.

### DeepSeek R1

Accuracy: 90. Result ID: 6a4632dd60b88bb339864ca1.

[Reporting paper](<https://www.sota2.com/research/paper/6a45f096dc71372d7795a3bf.md>)

Recorded evaluation configuration: {"queries":"20"}. This record does not assert independent reproduction.

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