# Natural Language Inference on AutoTNLI

Source: [Natural Language Inference on AutoTNLI](<https://www.sota2.com/research/sota/natural-language-inference-on-autotnli>)

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

Data updated: 2026-02-26T05:27:02.907Z

Evaluation of Natural Language Inference capabilities using the AutoTNLI dataset, typically 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 | Natural Language Inference |
| Dataset (including any stated split) | AutoTNLI |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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/natural-language-inference-on-autotnli.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CR | 72.5 | Not recorded | 68fa7a1a1e209131cea812fc |
| CoT | 63.2 | Not recorded | 68fa7a1a1e209131cea812fc |
| CoT-SC | 61.7 | Not recorded | 68fa7a1a1e209131cea812fc |
| Direct | 59.7 | Not recorded | 68fa7a1a1e209131cea812fc |
| CR | 57 | Not recorded | 68fa7a1a1e209131cea812fc |
| CoT | 54.1 | Not recorded | 68fa7a1a1e209131cea812fc |
| Direct | 52.6 | Not recorded | 68fa7a1a1e209131cea812fc |
| CoT-SC | 52.1 | Not recorded | 68fa7a1a1e209131cea812fc |
| Random | 50 | Not recorded | 68fa7a1a1e209131cea812fc |

### CR

Accuracy: 72.5. Result ID: 698b6d6d7a967eddb76e795d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a1a1e209131cea812fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a1a1e209131cea812fc.md>)

[Implementation](<https://github.com/iiis-ai/cumulative-reasoning>)

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

### CoT

Accuracy: 63.2. Result ID: 698b6d6d7a967eddb76e795b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a1a1e209131cea812fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"Model":"LLaMA-65B"}. This record does not assert independent reproduction.

### CoT-SC

Accuracy: 61.7. Result ID: 698b6d6d7a967eddb76e795c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a1a1e209131cea812fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

Recorded evaluation configuration: {"Model":"LLaMA-65B","k":16}. This record does not assert independent reproduction.

### Direct

Accuracy: 59.7. Result ID: 698b6d6d7a967eddb76e795a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a1a1e209131cea812fc.md>)

Recorded evaluation configuration: {"Model":"LLaMA-65B"}. This record does not assert independent reproduction.

### CR

Accuracy: 57. Result ID: 698b6d6d7a967eddb76e7959.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a1a1e209131cea812fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a1a1e209131cea812fc.md>)

[Implementation](<https://github.com/iiis-ai/cumulative-reasoning>)

Recorded evaluation configuration: {"Model":"LLaMA-13B","n":4}. This record does not assert independent reproduction.

### CoT

Accuracy: 54.1. Result ID: 698b6d6d7a967eddb76e7957.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a1a1e209131cea812fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"Model":"LLaMA-13B"}. This record does not assert independent reproduction.

### Direct

Accuracy: 52.6. Result ID: 698b6d6d7a967eddb76e7956.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a1a1e209131cea812fc.md>)

Recorded evaluation configuration: {"Model":"LLaMA-13B"}. This record does not assert independent reproduction.

### CoT-SC

Accuracy: 52.1. Result ID: 698b6d6d7a967eddb76e7958.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a1a1e209131cea812fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

Recorded evaluation configuration: {"Model":"LLaMA-13B","k":16}. This record does not assert independent reproduction.

### Random

Accuracy: 50. Result ID: 698b6d6d7a967eddb76e7955.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a1a1e209131cea812fc.md>)

Recorded evaluation configuration: {"Model":"-"}. This record does not assert independent reproduction.

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