# Aspect-Category-Opinion-Sentiment (ACOS) on Czech monolingual Source: [Aspect-Category-Opinion-Sentiment (ACOS) on Czech monolingual]() Collection index: [llms.txt]() Data updated: 2026-03-05T08:43:23.146Z Evaluation of Aspect-Category-Opinion-Sentiment (ACOS) performance on the Czech monolingual dataset, measured using F1 score. 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 | Aspect-Category-Opinion-Sentiment (ACOS) | | Dataset (including any stated split) | Czech monolingual | | Metric | F1 Score | | 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 - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | mT5 | 58.06 | Not recorded | 69a124eb2d603e6de3e3c32a | | Aya 23 8B | 57.46 | Not recorded | 69a124eb2d603e6de3e3c32a | | LLaMA 3.1 8B | 56.18 | Not recorded | 69a124eb2d603e6de3e3c32a | | Orca 2 13B | 53.85 | Not recorded | 69a124eb2d603e6de3e3c32a | | Gemma 3 12B | 48.45 | Not recorded | 69a124eb2d603e6de3e3c32a | | Gemma 3 4B | 44.54 | Not recorded | 69a124eb2d603e6de3e3c32a | | Gemma 3 27B | 39.35 | Not recorded | 69a124eb2d603e6de3e3c32a | | Gemma 3 27B | 35.43 | Not recorded | 69a124eb2d603e6de3e3c32a | | GPT-4o mini | 33.77 | Not recorded | 69a124eb2d603e6de3e3c32a | | LLaMA 3.3 70B | 33.76 | Not recorded | 69a124eb2d603e6de3e3c32a | | Gemma 3 12B | 33.41 | Not recorded | 69a124eb2d603e6de3e3c32a | | LLaMA 3.1 70B | 33.37 | Not recorded | 69a124eb2d603e6de3e3c32a | | GPT-4o mini | 33.05 | Not recorded | 69a124eb2d603e6de3e3c32a | | LLaMA 3.3 70B | 32.08 | Not recorded | 69a124eb2d603e6de3e3c32a | | Aya 23 35B | 30.67 | Not recorded | 69a124eb2d603e6de3e3c32a | | Gemma 3 12B | 28 | Not recorded | 69a124eb2d603e6de3e3c32a | | LLaMA 3.1 70B | 26.49 | Not recorded | 69a124eb2d603e6de3e3c32a | | Gemma 3 4B | 25.07 | Not recorded | 69a124eb2d603e6de3e3c32a | | Aya 23 35B | 23.18 | Not recorded | 69a124eb2d603e6de3e3c32a | | Orca 2 13B | 21.41 | Not recorded | 69a124eb2d603e6de3e3c32a | | Aya 23 8B | 20.65 | Not recorded | 69a124eb2d603e6de3e3c32a | | LLaMA 3.1 8B | 14.2 | Not recorded | 69a124eb2d603e6de3e3c32a | | Gemma 3 4B | 8.23 | Not recorded | 69a124eb2d603e6de3e3c32a | | Orca 2 13B | 8.09 | Not recorded | 69a124eb2d603e6de3e3c32a | | Aya 23 8B | 5.97 | Not recorded | 69a124eb2d603e6de3e3c32a | | LLaMA 3.1 8B | 3.5 | Not recorded | 69a124eb2d603e6de3e3c32a | ### mT5 F1 Score: 58.06. Result ID: 69a942176dbb7075b952c6e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Fine-tuning"}. This record does not assert independent reproduction. ### Aya 23 8B F1 Score: 57.46. Result ID: 69a942176dbb7075b952c6e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Fine-tuning"}. This record does not assert independent reproduction. ### LLaMA 3.1 8B F1 Score: 56.18. Result ID: 69a942176dbb7075b952c6ea. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Fine-tuning"}. This record does not assert independent reproduction. ### Orca 2 13B F1 Score: 53.85. Result ID: 69a942176dbb7075b952c6eb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Fine-tuning"}. This record does not assert independent reproduction. ### Gemma 3 12B F1 Score: 48.45. Result ID: 69a942176dbb7075b952c6e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Fine-tuning"}. This record does not assert independent reproduction. ### Gemma 3 4B F1 Score: 44.54. Result ID: 69a942176dbb7075b952c6e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Fine-tuning"}. This record does not assert independent reproduction. ### Gemma 3 27B F1 Score: 39.35. Result ID: 69a942176dbb7075b952c6e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Few-shot"}. This record does not assert independent reproduction. ### Gemma 3 27B F1 Score: 35.43. Result ID: 69a942176dbb7075b952c6d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### GPT-4o mini F1 Score: 33.77. Result ID: 69a942176dbb7075b952c6db. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### LLaMA 3.3 70B F1 Score: 33.76. Result ID: 69a942176dbb7075b952c6e3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Few-shot"}. This record does not assert independent reproduction. ### Gemma 3 12B F1 Score: 33.41. Result ID: 69a942176dbb7075b952c6df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Few-shot"}. This record does not assert independent reproduction. ### LLaMA 3.1 70B F1 Score: 33.37. Result ID: 69a942176dbb7075b952c6e2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Few-shot"}. This record does not assert independent reproduction. ### GPT-4o mini F1 Score: 33.05. Result ID: 69a942176dbb7075b952c6e5. [Reporting paper]() Recorded evaluation configuration: {"Type":"Few-shot"}. This record does not assert independent reproduction. ### LLaMA 3.3 70B F1 Score: 32.08. Result ID: 69a942176dbb7075b952c6d9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### Aya 23 35B F1 Score: 30.67. Result ID: 69a942176dbb7075b952c6dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Few-shot"}. This record does not assert independent reproduction. ### Gemma 3 12B F1 Score: 28. Result ID: 69a942176dbb7075b952c6d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### LLaMA 3.1 70B F1 Score: 26.49. Result ID: 69a942176dbb7075b952c6d8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### Gemma 3 4B F1 Score: 25.07. Result ID: 69a942176dbb7075b952c6de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Few-shot"}. This record does not assert independent reproduction. ### Aya 23 35B F1 Score: 23.18. Result ID: 69a942176dbb7075b952c6d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### Orca 2 13B F1 Score: 21.41. Result ID: 69a942176dbb7075b952c6e4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Few-shot"}. This record does not assert independent reproduction. ### Aya 23 8B F1 Score: 20.65. Result ID: 69a942176dbb7075b952c6dc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Few-shot"}. This record does not assert independent reproduction. ### LLaMA 3.1 8B F1 Score: 14.2. Result ID: 69a942176dbb7075b952c6e1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Few-shot"}. This record does not assert independent reproduction. ### Gemma 3 4B F1 Score: 8.23. Result ID: 69a942176dbb7075b952c6d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### Orca 2 13B F1 Score: 8.09. Result ID: 69a942176dbb7075b952c6da. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### Aya 23 8B F1 Score: 5.97. Result ID: 69a942176dbb7075b952c6d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### LLaMA 3.1 8B F1 Score: 3.5. Result ID: 69a942176dbb7075b952c6d7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.