# Natural Language Inference on LogicNLI

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

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

Data updated: 2026-02-26T05:32:51.335Z

Evaluation of Natural Language Inference performance on the LogicNLI 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 | Natural Language Inference |
| Dataset (including any stated split) | LogicNLI |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 26 of 26 |
| 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-logicnli.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| gemma-2-2b | 41 | Not recorded | 6993f6239ebc499c97409b3a |
| qwen-2.5-1.5b | 41 | Not recorded | 6993f6239ebc499c97409b3a |
| ministral-8b | 38 | Not recorded | 6993f6239ebc499c97409b3a |
| gemma-2-9b | 37 | Not recorded | 6993f6239ebc499c97409b3a |
| gemma-2-27b | 37 | Not recorded | 6993f6239ebc499c97409b3a |
| llama-3.2-3b | 37 | Not recorded | 6993f6239ebc499c97409b3a |
| llama-3.1-8b | 37 | Not recorded | 6993f6239ebc499c97409b3a |
| qwen-2.5-0.5b | 36 | Not recorded | 6993f6239ebc499c97409b3a |
| qwen-2.5-3b | 35 | Not recorded | 6993f6239ebc499c97409b3a |
| qwen-2.5-14b | 35 | Not recorded | 6993f6239ebc499c97409b3a |
| mistral-22b | 34 | Not recorded | 6993f6239ebc499c97409b3a |
| qwen-2.5-7b | 34 | Not recorded | 6993f6239ebc499c97409b3a |
| llama-3.2-1b | 33 | Not recorded | 6993f6239ebc499c97409b3a |
| qwen-2.5-14b | 27 | Not recorded | 6993f6239ebc499c97409b3a |
| gemma-2-27b | 24 | Not recorded | 6993f6239ebc499c97409b3a |
| gemma-2-9b | 23 | Not recorded | 6993f6239ebc499c97409b3a |
| gemma-2-2b | 22 | Not recorded | 6993f6239ebc499c97409b3a |
| llama-3.1-8b | 17 | Not recorded | 6993f6239ebc499c97409b3a |
| llama-3.2-3b | 15 | Not recorded | 6993f6239ebc499c97409b3a |
| mistral-22b | 14 | Not recorded | 6993f6239ebc499c97409b3a |
| qwen-2.5-0.5b | 12 | Not recorded | 6993f6239ebc499c97409b3a |
| llama-3.2-1b | 11 | Not recorded | 6993f6239ebc499c97409b3a |
| ministral-8b | 4 | Not recorded | 6993f6239ebc499c97409b3a |
| qwen-2.5-1.5b | 3 | Not recorded | 6993f6239ebc499c97409b3a |
| qwen-2.5-3b | 1 | Not recorded | 6993f6239ebc499c97409b3a |
| qwen-2.5-7b | 1 | Not recorded | 6993f6239ebc499c97409b3a |

### gemma-2-2b

Accuracy: 41. Result ID: 699a70b15698665ec4f97746.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### qwen-2.5-1.5b

Accuracy: 41. Result ID: 699a70b15698665ec4f97758.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### ministral-8b

Accuracy: 38. Result ID: 699a70b15698665ec4f97752.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### gemma-2-9b

Accuracy: 37. Result ID: 699a70b15698665ec4f97748.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### gemma-2-27b

Accuracy: 37. Result ID: 699a70b15698665ec4f9774a.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### llama-3.2-3b

Accuracy: 37. Result ID: 699a70b15698665ec4f9774e.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### llama-3.1-8b

Accuracy: 37. Result ID: 699a70b15698665ec4f97750.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### qwen-2.5-0.5b

Accuracy: 36. Result ID: 699a70b15698665ec4f97756.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### qwen-2.5-3b

Accuracy: 35. Result ID: 699a70b15698665ec4f9775a.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### qwen-2.5-14b

Accuracy: 35. Result ID: 699a70b15698665ec4f9775e.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### mistral-22b

Accuracy: 34. Result ID: 699a70b15698665ec4f97754.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### qwen-2.5-7b

Accuracy: 34. Result ID: 699a70b15698665ec4f9775c.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### llama-3.2-1b

Accuracy: 33. Result ID: 699a70b15698665ec4f9774c.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"NL2LOGIC"}. This record does not assert independent reproduction.

### qwen-2.5-14b

Accuracy: 27. Result ID: 699a70b15698665ec4f9775d.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

### gemma-2-27b

Accuracy: 24. Result ID: 699a70b15698665ec4f97749.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

### gemma-2-9b

Accuracy: 23. Result ID: 699a70b15698665ec4f97747.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

### gemma-2-2b

Accuracy: 22. Result ID: 699a70b15698665ec4f97745.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

### llama-3.1-8b

Accuracy: 17. Result ID: 699a70b15698665ec4f9774f.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

### llama-3.2-3b

Accuracy: 15. Result ID: 699a70b15698665ec4f9774d.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

### mistral-22b

Accuracy: 14. Result ID: 699a70b15698665ec4f97753.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

### qwen-2.5-0.5b

Accuracy: 12. Result ID: 699a70b15698665ec4f97755.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

### llama-3.2-1b

Accuracy: 11. Result ID: 699a70b15698665ec4f9774b.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

### ministral-8b

Accuracy: 4. Result ID: 699a70b15698665ec4f97751.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

### qwen-2.5-1.5b

Accuracy: 3. Result ID: 699a70b15698665ec4f97757.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

### qwen-2.5-3b

Accuracy: 1. Result ID: 699a70b15698665ec4f97759.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

### qwen-2.5-7b

Accuracy: 1. Result ID: 699a70b15698665ec4f9775b.

[Reporting paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f6239ebc499c97409b3a.md>)

Recorded evaluation configuration: {"Decoding Method":"GCD"}. This record does not assert independent reproduction.

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