# Review Score Generation on ICML 2025 Source: [Review Score Generation on ICML 2025]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:36:21.469Z Evaluation of model performance on generating review scores using the ICML 2025 dataset, typically measured using the Average Review Score metric. 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 | Review Score Generation | | Dataset (including any stated split) | ICML 2025 | | Metric | Avg Review Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [Avg Review Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Avg Review Score | Result date | Report paper | | --- | --- | --- | --- | | PAA | 3.7 | Not recorded | 6965d1746343fa78c8323494 | | PAA | 3.6 | Not recorded | 6965d1746343fa78c8323494 | | PAA | 3.4 | Not recorded | 6965d1746343fa78c8323494 | | PAA | 3.2 | Not recorded | 6965d1746343fa78c8323494 | | PAA | 3.2 | Not recorded | 6965d1746343fa78c8323494 | | PAA | 3.1 | Not recorded | 6965d1746343fa78c8323494 | | PAA | 3.1 | Not recorded | 6965d1746343fa78c8323494 | | PAA | 3 | Not recorded | 6965d1746343fa78c8323494 | | Paraphrase | 2.3 | Not recorded | 6965d1746343fa78c8323494 | | Original | 1.9 | Not recorded | 6965d1746343fa78c8323494 | ### PAA Avg Review Score: 3.7. Result ID: 6996900c5698665ec4d90181. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacking Model":"Sonnet 4","Input Format":"Full-paper PDF"}. This record does not assert independent reproduction. ### PAA Avg Review Score: 3.6. Result ID: 6996900c5698665ec4d90180. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacking Model":"Sonnet 4","Input Format":"Abstract-only"}. This record does not assert independent reproduction. ### PAA Avg Review Score: 3.4. Result ID: 6996900c5698665ec4d9017d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacking Model":"GPT-4o","Input Format":"Full-paper PDF"}. This record does not assert independent reproduction. ### PAA Avg Review Score: 3.2. Result ID: 6996900c5698665ec4d9017f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacking Model":"Gemini 2.5","Input Format":"Full-paper PDF"}. This record does not assert independent reproduction. ### PAA Avg Review Score: 3.2. Result ID: 6996900c5698665ec4d90183. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacking Model":"Qwen 3","Input Format":"Abstract-only"}. This record does not assert independent reproduction. ### PAA Avg Review Score: 3.1. Result ID: 6996900c5698665ec4d9017c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacking Model":"GPT-4o","Input Format":"Abstract-only"}. This record does not assert independent reproduction. ### PAA Avg Review Score: 3.1. Result ID: 6996900c5698665ec4d90182. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacking Model":"OLMo 3","Input Format":"Abstract-only"}. This record does not assert independent reproduction. ### PAA Avg Review Score: 3. Result ID: 6996900c5698665ec4d9017e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacking Model":"Gemini 2.5","Input Format":"Abstract-only"}. This record does not assert independent reproduction. ### Paraphrase Avg Review Score: 2.3. Result ID: 6996900c5698665ec4d9017b. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Original Avg Review Score: 1.9. Result ID: 6996900c5698665ec4d9017a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.