# Natural Language Understanding on EuroEval Italian

Source: [Natural Language Understanding on EuroEval Italian](<https://www.sota2.com/research/sota/natural-language-understanding-on-euroeval-italian>)

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

Data updated: 2026-05-27T08:00:28.109Z

Evaluation of model performance on the Italian subset of the EuroEval benchmark suite, focusing on Natural Language Understanding capabilities.

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 Understanding |
| Dataset (including any stated split) | EuroEval Italian |
| Metric | EuroEval Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [EuroEval Score](<https://www.sota2.com/research/sota/natural-language-understanding-on-euroeval-italian.md?metric=EuroEval%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | EuroEval Score | Result date | Report paper |
| --- | --- | --- | --- |
| EuroLLM-9B (Base) | 54.3 | Not recorded | 6a167aa3dbd7150506f80031 |
| aya-3B (Base) | 51.6 | Not recorded | 6a167aa3dbd7150506f80031 |
| aya-3B (Multilingual All Lang SFT) | 11.3 | Not recorded | 6a167aa3dbd7150506f80031 |
| aya-3B (Monolingual In-lang SFT) | 10.7 | Not recorded | 6a167aa3dbd7150506f80031 |
| aya-3B (Monolingual Max-R SFT) | 10.6 | Not recorded | 6a167aa3dbd7150506f80031 |
| aya-3B (Multilingual Max-R SFT) | 10.5 | Not recorded | 6a167aa3dbd7150506f80031 |
| EuroLLM-9B (Multilingual All Lang SFT) | 9.9 | Not recorded | 6a167aa3dbd7150506f80031 |
| EuroLLM-9B (Monolingual In-lang SFT) | 7.6 | Not recorded | 6a167aa3dbd7150506f80031 |
| EuroLLM-9B (Multilingual Max-R SFT) | 5 | Not recorded | 6a167aa3dbd7150506f80031 |
| EuroLLM-9B (Monolingual Paired DPO) | 3.6 | Not recorded | 6a167aa3dbd7150506f80031 |
| EuroLLM-9B (Multilingual Paired DPO) | 1.3 | Not recorded | 6a167aa3dbd7150506f80031 |
| EuroLLM-9B (Monolingual Max-R SFT) | 1.2 | Not recorded | 6a167aa3dbd7150506f80031 |
| aya-3B (Multilingual Paired DPO) | 0.6 | Not recorded | 6a167aa3dbd7150506f80031 |
| aya-3B (Monolingual Paired DPO) | 0.4 | Not recorded | 6a167aa3dbd7150506f80031 |

### EuroLLM-9B (Base)

EuroEval Score: 54.3. Result ID: 6a16a41ffbc373592c0f98ad.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

Recorded evaluation configuration: {"Language model":"EuroLLM-9B"}. This record does not assert independent reproduction.

### aya-3B (Base)

EuroEval Score: 51.6. Result ID: 6a16a41ffbc373592c0f98a6.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b399ef0636e5bf4afbc93b.md>)

Recorded evaluation configuration: {"Language model":"aya-3B"}. This record does not assert independent reproduction.

### aya-3B (Multilingual All Lang SFT)

EuroEval Score: 11.3. Result ID: 6a16a41ffbc373592c0f98aa.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

Recorded evaluation configuration: {"Regime":"Multilingual","Post-training":"SFT","Data":"All Lang"}. This record does not assert independent reproduction.

### aya-3B (Monolingual In-lang SFT)

EuroEval Score: 10.7. Result ID: 6a16a41ffbc373592c0f98a7.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

Recorded evaluation configuration: {"Regime":"Monolingual","Post-training":"SFT","Data":"In-lang"}. This record does not assert independent reproduction.

### aya-3B (Monolingual Max-R SFT)

EuroEval Score: 10.6. Result ID: 6a16a41ffbc373592c0f98a8.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Implementation](<https://github.com/jjzha/CroCo>)

Recorded evaluation configuration: {"Regime":"Monolingual","Post-training":"SFT","Data":"Max-R"}. This record does not assert independent reproduction.

### aya-3B (Multilingual Max-R SFT)

EuroEval Score: 10.5. Result ID: 6a16a41ffbc373592c0f98ab.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Implementation](<https://github.com/jjzha/CroCo>)

Recorded evaluation configuration: {"Regime":"Multilingual","Post-training":"SFT","Data":"Max-R"}. This record does not assert independent reproduction.

### EuroLLM-9B (Multilingual All Lang SFT)

EuroEval Score: 9.9. Result ID: 6a16a41ffbc373592c0f98b1.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

Recorded evaluation configuration: {"Regime":"Multilingual","Post-training":"SFT","Data":"All Lang"}. This record does not assert independent reproduction.

### EuroLLM-9B (Monolingual In-lang SFT)

EuroEval Score: 7.6. Result ID: 6a16a41ffbc373592c0f98ae.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

Recorded evaluation configuration: {"Regime":"Monolingual","Post-training":"SFT","Data":"In-lang"}. This record does not assert independent reproduction.

### EuroLLM-9B (Multilingual Max-R SFT)

EuroEval Score: 5. Result ID: 6a16a41ffbc373592c0f98b2.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Implementation](<https://github.com/jjzha/CroCo>)

Recorded evaluation configuration: {"Regime":"Multilingual","Post-training":"SFT","Data":"Max-R"}. This record does not assert independent reproduction.

### EuroLLM-9B (Monolingual Paired DPO)

EuroEval Score: 3.6. Result ID: 6a16a41ffbc373592c0f98b0.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Implementation](<https://github.com/jjzha/CroCo>)

Recorded evaluation configuration: {"Regime":"Monolingual","Post-training":"DPO","Data":"Paired"}. This record does not assert independent reproduction.

### EuroLLM-9B (Multilingual Paired DPO)

EuroEval Score: 1.3. Result ID: 6a16a41ffbc373592c0f98b3.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Implementation](<https://github.com/jjzha/CroCo>)

Recorded evaluation configuration: {"Regime":"Multilingual","Post-training":"DPO","Data":"Paired"}. This record does not assert independent reproduction.

### EuroLLM-9B (Monolingual Max-R SFT)

EuroEval Score: 1.2. Result ID: 6a16a41ffbc373592c0f98af.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Implementation](<https://github.com/jjzha/CroCo>)

Recorded evaluation configuration: {"Regime":"Monolingual","Post-training":"SFT","Data":"Max-R"}. This record does not assert independent reproduction.

### aya-3B (Multilingual Paired DPO)

EuroEval Score: 0.6. Result ID: 6a16a41ffbc373592c0f98ac.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Implementation](<https://github.com/jjzha/CroCo>)

Recorded evaluation configuration: {"Regime":"Multilingual","Post-training":"DPO","Data":"Paired"}. This record does not assert independent reproduction.

### aya-3B (Monolingual Paired DPO)

EuroEval Score: 0.4. Result ID: 6a16a41ffbc373592c0f98a9.

[Reporting paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167aa3dbd7150506f80031.md>)

[Implementation](<https://github.com/jjzha/CroCo>)

Recorded evaluation configuration: {"Regime":"Monolingual","Post-training":"DPO","Data":"Paired"}. This record does not assert independent reproduction.

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