# Multilingual Logical Reasoning on CrossLogiQA

Source: [Multilingual Logical Reasoning on CrossLogiQA](<https://www.sota2.com/research/sota/multilingual-logical-reasoning-on-crosslogiqa>)

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

Data updated: 2026-04-15T07:12:08.726Z

Evaluation of model performance on multilingual logical reasoning tasks using the CrossLogiQA dataset, reporting scores across English, Chinese, Indonesian, and Consensus.

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 | Multilingual Logical Reasoning |
| Dataset (including any stated split) | CrossLogiQA |
| Metric | Accuracy (en) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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 (en)](<https://www.sota2.com/research/sota/multilingual-logical-reasoning-on-crosslogiqa.md?metric=Accuracy%20(en)>): Higher is better; unit: PERCENT.

- [Accuracy (zh)](<https://www.sota2.com/research/sota/multilingual-logical-reasoning-on-crosslogiqa.md?metric=Accuracy%20(zh)>): Higher is better; unit: PERCENT.

- [Accuracy (id)](<https://www.sota2.com/research/sota/multilingual-logical-reasoning-on-crosslogiqa.md?metric=Accuracy%20(id)>): Higher is better; unit: PERCENT.

- [Accuracy (Consensus)](<https://www.sota2.com/research/sota/multilingual-logical-reasoning-on-crosslogiqa.md?metric=Accuracy%20(Consensus)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (en) | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen2.5-7B-AdaMCOT | 75 | Not recorded | 68fa7a601e209131cea82b5f |
| Qwen2.5-7B-Instruction | 69.3 | Not recorded | 68fa7a601e209131cea82b5f |
| LLaMA3.1-8B-AdaMCOT | 64.2 | Not recorded | 68fa7a601e209131cea82b5f |
| LLaMA3.1-8B-Instruction | 61.4 | Not recorded | 68fa7a601e209131cea82b5f |

### Qwen2.5-7B-AdaMCOT

Accuracy (en): 75. Result ID: 69df390f47f34ce924c7860e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b5f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b5f.md>)

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

### Qwen2.5-7B-Instruction

Accuracy (en): 69.3. Result ID: 69df390f47f34ce924c7860d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b5f.md>)

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

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

### LLaMA3.1-8B-AdaMCOT

Accuracy (en): 64.2. Result ID: 69df390f47f34ce924c7860c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b5f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b5f.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA3.1-8B"}. This record does not assert independent reproduction.

### LLaMA3.1-8B-Instruction

Accuracy (en): 61.4. Result ID: 69df390f47f34ce924c7860b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b5f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Backbone":"LLaMA3.1-8B"}. This record does not assert independent reproduction.

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