# Last-letter-concatenation on Last-letter-concatenation 12 words (out-of-distribution)

Source: [Last-letter-concatenation on Last-letter-concatenation 12 words (out-of-distribution)](<https://www.sota2.com/research/sota/last-letter-concatenation-on-last-letter-concatenation-12-words-out-of-distribution>)

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

Data updated: 2026-02-27T09:24:51.131Z

Evaluation of the Last-letter-concatenation task on the out-of-distribution subset of the 12-word version of the Last-letter-concatenation dataset, measured by 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 | Last-letter-concatenation |
| Dataset (including any stated split) | Last-letter-concatenation 12 words (out-of-distribution) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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/last-letter-concatenation-on-last-letter-concatenation-12-words-out-of-distribution.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SKiC | 100 | Not recorded | 68fa74201e209131cea5fd25 |
| SKiC | 98 | Not recorded | 68fa74201e209131cea5fd25 |
| LtM | 88 | Not recorded | 68fa74201e209131cea5fd25 |
| 4-shots | 85 | Not recorded | 68fa74201e209131cea5fd25 |
| CoT | 85 | Not recorded | 68fa74201e209131cea5fd25 |
| LtM | 80 | Not recorded | 68fa74201e209131cea5fd25 |
| zero-shot | 77 | Not recorded | 68fa74201e209131cea5fd25 |
| SKiC | 36 | Not recorded | 68fa74201e209131cea5fd25 |
| CoT | 31 | Not recorded | 68fa74201e209131cea5fd25 |
| LtM | 25 | Not recorded | 68fa74201e209131cea5fd25 |
| CoT | 20 | Not recorded | 68fa74201e209131cea5fd25 |
| 4-shots | 10 | Not recorded | 68fa74201e209131cea5fd25 |
| zero-shot | 0 | Not recorded | 68fa74201e209131cea5fd25 |
| 4-shots | 0 | Not recorded | 68fa74201e209131cea5fd25 |
| zero-shot | 0 | Not recorded | 68fa74201e209131cea5fd25 |

### SKiC

Accuracy: 100. Result ID: 69a162d835dfcabb00e6b8db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

Recorded evaluation configuration: {"Model":"ChatGPT","#-shots":"2"}. This record does not assert independent reproduction.

### SKiC

Accuracy: 98. Result ID: 69a162d835dfcabb00e6b8d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

Recorded evaluation configuration: {"Model":"text-davinci-003","#-shots":"2"}. This record does not assert independent reproduction.

### LtM

Accuracy: 88. Result ID: 69a162d835dfcabb00e6b8da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f131e209131cea43b97.md>)

Recorded evaluation configuration: {"Model":"ChatGPT","#-shots":"4"}. This record does not assert independent reproduction.

### 4-shots

Accuracy: 85. Result ID: 69a162d835dfcabb00e6b8d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"ChatGPT","#-shots":"4"}. This record does not assert independent reproduction.

### CoT

Accuracy: 85. Result ID: 69a162d835dfcabb00e6b8d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"ChatGPT","#-shots":"4"}. This record does not assert independent reproduction.

### LtM

Accuracy: 80. Result ID: 69a162d835dfcabb00e6b8d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f131e209131cea43b97.md>)

Recorded evaluation configuration: {"Model":"text-davinci-003","#-shots":"4"}. This record does not assert independent reproduction.

### zero-shot

Accuracy: 77. Result ID: 69a162d835dfcabb00e6b8d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"ChatGPT","#-shots":"0"}. This record does not assert independent reproduction.

### SKiC

Accuracy: 36. Result ID: 69a162d835dfcabb00e6b8d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

Recorded evaluation configuration: {"Model":"LLAMA-65B","#-shots":"2"}. This record does not assert independent reproduction.

### CoT

Accuracy: 31. Result ID: 69a162d835dfcabb00e6b8d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"text-davinci-003","#-shots":"4"}. This record does not assert independent reproduction.

### LtM

Accuracy: 25. Result ID: 69a162d835dfcabb00e6b8d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f131e209131cea43b97.md>)

Recorded evaluation configuration: {"Model":"LLAMA-65B","#-shots":"4"}. This record does not assert independent reproduction.

### CoT

Accuracy: 20. Result ID: 69a162d835dfcabb00e6b8cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"LLAMA-65B","#-shots":"4"}. This record does not assert independent reproduction.

### 4-shots

Accuracy: 10. Result ID: 69a162d835dfcabb00e6b8d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"text-davinci-003","#-shots":"4"}. This record does not assert independent reproduction.

### zero-shot

Accuracy: 0. Result ID: 69a162d835dfcabb00e6b8cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"LLAMA-65B","#-shots":"0"}. This record does not assert independent reproduction.

### 4-shots

Accuracy: 0. Result ID: 69a162d835dfcabb00e6b8ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"LLAMA-65B","#-shots":"4"}. This record does not assert independent reproduction.

### zero-shot

Accuracy: 0. Result ID: 69a162d835dfcabb00e6b8d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fd25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"text-davinci-003","#-shots":"0"}. This record does not assert independent reproduction.

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