# Logic Reasoning on K&K Logic Puzzles OOD

Source: [Logic Reasoning on K&K Logic Puzzles OOD](<https://www.sota2.com/research/sota/logic-reasoning-on-k-and-k-logic-puzzles-ood>)

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

Data updated: 2026-03-10T09:32:35.314Z

Evaluation of model performance on the K&K Logic Puzzles dataset focusing on Out-of-Distribution (OOD) reasoning capabilities, measured by specific score thresholds (2 and 8) and overall average.

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 | Logic Reasoning |
| Dataset (including any stated split) | K&K Logic Puzzles OOD |
| Metric | Score Threshold 2 (OOD) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 25 of 25 |
| 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

- [Score Threshold 2 (OOD)](<https://www.sota2.com/research/sota/logic-reasoning-on-k-and-k-logic-puzzles-ood.md?metric=Score%20Threshold%202%20(OOD)>): Higher is better; unit: PERCENT.

- [Score Threshold 8 (OOD)](<https://www.sota2.com/research/sota/logic-reasoning-on-k-and-k-logic-puzzles-ood.md?metric=Score%20Threshold%208%20(OOD)>): Higher is better; unit: PERCENT.

- [Average Score (OOD)](<https://www.sota2.com/research/sota/logic-reasoning-on-k-and-k-logic-puzzles-ood.md?metric=Average%20Score%20(OOD)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Score Threshold 2 (OOD) | Result date | Report paper |
| --- | --- | --- | --- |
| o3-mini-high | 99 | Not recorded | 68fa7b961e209131cea894b1 |
| MeRF | 99 | Not recorded | 68fa7b961e209131cea894b1 |
| MeRF | 99 | Not recorded | 68fa7b961e209131cea894b1 |
| Deepseek-R1 | 91 | Not recorded | 68fa7b961e209131cea894b1 |
| RLVR | 90 | Not recorded | 68fa7b961e209131cea894b1 |
| RLVR | 90 | Not recorded | 68fa7b961e209131cea894b1 |
| o1-2024-12-17 | 83 | Not recorded | 68fa7b961e209131cea894b1 |
| MeRF | 76 | Not recorded | 68fa7b961e209131cea894b1 |
| MeRF | 76 | Not recorded | 68fa7b961e209131cea894b1 |
| RLVR | 71 | Not recorded | 68fa7b961e209131cea894b1 |
| MeRF | 70 | Not recorded | 68fa7b961e209131cea894b1 |
| GPT-4o | 68 | Not recorded | 68fa7b961e209131cea894b1 |
| GPT-4o-mini | 63 | Not recorded | 68fa7b961e209131cea894b1 |
| Qwen2.5-14B-Instruct | 63 | Not recorded | 68fa7b961e209131cea894b1 |
| RLVR | 60 | Not recorded | 68fa7b961e209131cea894b1 |
| RLVR | 59 | Not recorded | 68fa7b961e209131cea894b1 |
| Qwen2.5-7B-Instruct-1M | 49 | Not recorded | 68fa7b961e209131cea894b1 |
| Qwen2.5-7B-Instruct | 43 | Not recorded | 68fa7b961e209131cea894b1 |
| MeRF | 43 | Not recorded | 68fa7b961e209131cea894b1 |
| Qwen2.5-7B-Base | 41 | Not recorded | 68fa7b961e209131cea894b1 |
| Deepseek-Math-7B | 35 | Not recorded | 68fa7b961e209131cea894b1 |
| DeepSeek-R1-Distill-Qwen-1.5B | 30 | Not recorded | 68fa7b961e209131cea894b1 |
| RLVR | 29 | Not recorded | 68fa7b961e209131cea894b1 |
| NuminaMath-7B-CoT | 28 | Not recorded | 68fa7b961e209131cea894b1 |
| DeepSeek-R1-Distill-Llama-8B | 24 | Not recorded | 68fa7b961e209131cea894b1 |

### o3-mini-high

Score Threshold 2 (OOD): 99. Result ID: 69afe52b6dbb7075b9589e14.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MeRF

Score Threshold 2 (OOD): 99. Result ID: 69afe52b6dbb7075b9589e26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction.

### MeRF

Score Threshold 2 (OOD): 99. Result ID: 69afe52b6dbb7075b9589e2c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Llama-8B"}. This record does not assert independent reproduction.

### Deepseek-R1

Score Threshold 2 (OOD): 91. Result ID: 69afe52b6dbb7075b9589e16.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RLVR

Score Threshold 2 (OOD): 90. Result ID: 69afe52b6dbb7075b9589e25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78121e209131cea76a04.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction.

### RLVR

Score Threshold 2 (OOD): 90. Result ID: 69afe52b6dbb7075b9589e2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78121e209131cea76a04.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Llama-8B"}. This record does not assert independent reproduction.

### o1-2024-12-17

Score Threshold 2 (OOD): 83. Result ID: 69afe52b6dbb7075b9589e15.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76691e209131cea6ccaa.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MeRF

Score Threshold 2 (OOD): 76. Result ID: 69afe52b6dbb7075b9589e20.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction.

### MeRF

Score Threshold 2 (OOD): 76. Result ID: 69afe52b6dbb7075b9589e23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct-1M"}. This record does not assert independent reproduction.

### RLVR

Score Threshold 2 (OOD): 71. Result ID: 69afe52b6dbb7075b9589e1f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78121e209131cea76a04.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction.

### MeRF

Score Threshold 2 (OOD): 70. Result ID: 69afe52b6dbb7075b9589e1d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Base"}. This record does not assert independent reproduction.

### GPT-4o

Score Threshold 2 (OOD): 68. Result ID: 69afe52b6dbb7075b9589e17.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-4o-mini

Score Threshold 2 (OOD): 63. Result ID: 69afe52b6dbb7075b9589e18.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen2.5-14B-Instruct

Score Threshold 2 (OOD): 63. Result ID: 69afe52b6dbb7075b9589e24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767e1e209131cea6d6a7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RLVR

Score Threshold 2 (OOD): 60. Result ID: 69afe52b6dbb7075b9589e22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78121e209131cea76a04.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct-1M"}. This record does not assert independent reproduction.

### RLVR

Score Threshold 2 (OOD): 59. Result ID: 69afe52b6dbb7075b9589e1c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78121e209131cea76a04.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Base"}. This record does not assert independent reproduction.

### Qwen2.5-7B-Instruct-1M

Score Threshold 2 (OOD): 49. Result ID: 69afe52b6dbb7075b9589e21.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767e1e209131cea6d6a7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen2.5-7B-Instruct

Score Threshold 2 (OOD): 43. Result ID: 69afe52b6dbb7075b9589e1e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767e1e209131cea6d6a7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MeRF

Score Threshold 2 (OOD): 43. Result ID: 69afe52b6dbb7075b9589e29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction.

### Qwen2.5-7B-Base

Score Threshold 2 (OOD): 41. Result ID: 69afe52b6dbb7075b9589e1b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767e1e209131cea6d6a7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Deepseek-Math-7B

Score Threshold 2 (OOD): 35. Result ID: 69afe52b6dbb7075b9589e1a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DeepSeek-R1-Distill-Qwen-1.5B

Score Threshold 2 (OOD): 30. Result ID: 69afe52b6dbb7075b9589e27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RLVR

Score Threshold 2 (OOD): 29. Result ID: 69afe52b6dbb7075b9589e28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78121e209131cea76a04.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction.

### NuminaMath-7B-CoT

Score Threshold 2 (OOD): 28. Result ID: 69afe52b6dbb7075b9589e19.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DeepSeek-R1-Distill-Llama-8B

Score Threshold 2 (OOD): 24. Result ID: 69afe52b6dbb7075b9589e2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b961e209131cea894b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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