# Binary equivalence judgment on French medical OEQA Source: [Binary equivalence judgment on French medical OEQA]() Collection index: [llms.txt]() Data updated: 2026-03-05T09:18:01.509Z Evaluation of model performance on the French medical OEQA dataset for binary equivalence judgment, measured using Precision, Recall, F1 score, Accuracy, and Pearson correlation. 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 | Binary equivalence judgment | | Dataset (including any stated split) | French medical OEQA | | Metric | Precision | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [Precision](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. - [Pearson Correlation Coefficient](): Higher is better; unit: PERCENT. ## Recorded results | Method | Precision | Result date | Report paper | | --- | --- | --- | --- | | GPT-5.1 | 76.19 | Not recorded | 69a90e182d603e6de3e40920 | | Gemini-2.5-Pro | 65.35 | Not recorded | 69a90e182d603e6de3e40920 | | Qwen-80B | 64.62 | Not recorded | 69a90e182d603e6de3e40920 | | MedGemma-27B | 52.17 | Not recorded | 69a90e182d603e6de3e40920 | | GRPO-Phi-3.5-mini | 51.91 | Not recorded | 69a90e182d603e6de3e40920 | | SFT-Phi-3.5-mini | 38.81 | Not recorded | 69a90e182d603e6de3e40920 | | Phi-3.5-mini | 35.94 | Not recorded | 69a90e182d603e6de3e40920 | ### GPT-5.1 Precision: 76.19. Result ID: 69a9494c6dbb7075b952fe10. [Reporting paper]() Recorded evaluation configuration: {"Judge":"GPT-5.1"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Precision: 65.35. Result ID: 69a9494c6dbb7075b952fe0f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Judge":"Gemini-2.5-Pro"}. This record does not assert independent reproduction. ### Qwen-80B Precision: 64.62. Result ID: 69a9494c6dbb7075b952fe0e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Judge":"Qwen-80B"}. This record does not assert independent reproduction. ### MedGemma-27B Precision: 52.17. Result ID: 69a9494c6dbb7075b952fe0d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Judge":"MedGemma-27B"}. This record does not assert independent reproduction. ### GRPO-Phi-3.5-mini Precision: 51.91. Result ID: 69a9494c6dbb7075b952fe13. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Judge":"GRPO-Phi-3.5-mini"}. This record does not assert independent reproduction. ### SFT-Phi-3.5-mini Precision: 38.81. Result ID: 69a9494c6dbb7075b952fe12. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Judge":"SFT-Phi-3.5-mini"}. This record does not assert independent reproduction. ### Phi-3.5-mini Precision: 35.94. Result ID: 69a9494c6dbb7075b952fe11. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Judge":"Phi-3.5-mini"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.