# Claim-level rating prediction on FORA Source: [Claim-level rating prediction on FORA]() Collection index: [llms.txt]() Data updated: 2026-04-20T06:03:40.181Z Evaluation of model performance on predicting claim-level ratings (such as credibility, novelty, or scope) using the FORA dataset. 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 | Claim-level rating prediction | | Dataset (including any stated split) | FORA | | Metric | CIG Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 25 of 25 | | 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 - [CIG Score](): Higher is better; unit: PERCENT. - [Novelty Score](): Higher is better; unit: PERCENT. - [Relevance Score](): Higher is better; unit: PERCENT. - [Scope Score](): Higher is better; unit: PERCENT. - [Mean Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | CIG Score | Result date | Report paper | | --- | --- | --- | --- | | Gemini-2.5-Flash | 65.4 | Not recorded | 69e5b3137d0172140ec7e032 | | GPT-5-Mini | 64.6 | Not recorded | 69e5b3137d0172140ec7e032 | | Qwen3-4B | 64.3 | Not recorded | 69e5b3137d0172140ec7e032 | | GPT-5-Mini | 62.2 | Not recorded | 69e5b3137d0172140ec7e032 | | Qwen3-4B | 62.2 | Not recorded | 69e5b3137d0172140ec7e032 | | Qwen3-4B | 61.9 | Not recorded | 69e5b3137d0172140ec7e032 | | GPT-5 | 59.4 | Not recorded | 69e5b3137d0172140ec7e032 | | GPT-5-Mini | 59.1 | Not recorded | 69e5b3137d0172140ec7e032 | | Gemini-2.5-Flash | 58.9 | Not recorded | 69e5b3137d0172140ec7e032 | | Gemini-2.5-Flash | 58.8 | Not recorded | 69e5b3137d0172140ec7e032 | | Qwen3-4B | 57.9 | Not recorded | 69e5b3137d0172140ec7e032 | | GPT-5 | 57.2 | Not recorded | 69e5b3137d0172140ec7e032 | | GPT-5-Mini | 56.9 | Not recorded | 69e5b3137d0172140ec7e032 | | Gemini-2.5-Flash | 56.3 | Not recorded | 69e5b3137d0172140ec7e032 | | Gemini-2.5-Flash | 56 | Not recorded | 69e5b3137d0172140ec7e032 | | GPT-5-Mini | 55.1 | Not recorded | 69e5b3137d0172140ec7e032 | | Gemini-2.5-Pro | 53.5 | Not recorded | 69e5b3137d0172140ec7e032 | | Qwen3-4B | 53.5 | Not recorded | 69e5b3137d0172140ec7e032 | | GPT-5 | 53.1 | Not recorded | 69e5b3137d0172140ec7e032 | | Gemini-2.5-Pro | 52.7 | Not recorded | 69e5b3137d0172140ec7e032 | | GPT-5 | 52 | Not recorded | 69e5b3137d0172140ec7e032 | | Gemini-2.5-Pro | 52 | Not recorded | 69e5b3137d0172140ec7e032 | | Gemini-2.5-Pro | 51.8 | Not recorded | 69e5b3137d0172140ec7e032 | | GPT-5 | 51.2 | Not recorded | 69e5b3137d0172140ec7e032 | | Gemini-2.5-Pro | 50.5 | Not recorded | 69e5b3137d0172140ec7e032 | ### Gemini-2.5-Flash CIG Score: 65.4. Result ID: 69e5c18247f34ce924cb2d77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"No Knowledge"}. This record does not assert independent reproduction. ### GPT-5-Mini CIG Score: 64.6. Result ID: 69e5c18247f34ce924cb2d6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"No Knowledge"}. This record does not assert independent reproduction. ### Qwen3-4B CIG Score: 64.3. Result ID: 69e5c18247f34ce924cb2d7b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Memory"}. This record does not assert independent reproduction. ### GPT-5-Mini CIG Score: 62.2. Result ID: 69e5c18247f34ce924cb2d6e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Short Prior"}. This record does not assert independent reproduction. ### Qwen3-4B CIG Score: 62.2. Result ID: 69e5c18247f34ce924cb2d7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Full"}. This record does not assert independent reproduction. ### Qwen3-4B CIG Score: 61.9. Result ID: 69e5c18247f34ce924cb2d7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"No Knowledge"}. This record does not assert independent reproduction. ### GPT-5 CIG Score: 59.4. Result ID: 69e5c18247f34ce924cb2d68. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"No Knowledge"}. This record does not assert independent reproduction. ### GPT-5-Mini CIG Score: 59.1. Result ID: 69e5c18247f34ce924cb2d6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Memory"}. This record does not assert independent reproduction. ### Gemini-2.5-Flash CIG Score: 58.9. Result ID: 69e5c18247f34ce924cb2d79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Summary"}. This record does not assert independent reproduction. ### Gemini-2.5-Flash CIG Score: 58.8. Result ID: 69e5c18247f34ce924cb2d78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Short Prior"}. This record does not assert independent reproduction. ### Qwen3-4B CIG Score: 57.9. Result ID: 69e5c18247f34ce924cb2d7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Summary"}. This record does not assert independent reproduction. ### GPT-5 CIG Score: 57.2. Result ID: 69e5c18247f34ce924cb2d69. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Short Prior"}. This record does not assert independent reproduction. ### GPT-5-Mini CIG Score: 56.9. Result ID: 69e5c18247f34ce924cb2d6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Summary"}. This record does not assert independent reproduction. ### Gemini-2.5-Flash CIG Score: 56.3. Result ID: 69e5c18247f34ce924cb2d75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Full"}. This record does not assert independent reproduction. ### Gemini-2.5-Flash CIG Score: 56. Result ID: 69e5c18247f34ce924cb2d76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Memory"}. This record does not assert independent reproduction. ### GPT-5-Mini CIG Score: 55.1. Result ID: 69e5c18247f34ce924cb2d6b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Full"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro CIG Score: 53.5. Result ID: 69e5c18247f34ce924cb2d72. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"No Knowledge"}. This record does not assert independent reproduction. ### Qwen3-4B CIG Score: 53.5. Result ID: 69e5c18247f34ce924cb2d7d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Short Prior"}. This record does not assert independent reproduction. ### GPT-5 CIG Score: 53.1. Result ID: 69e5c18247f34ce924cb2d67. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Memory"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro CIG Score: 52.7. Result ID: 69e5c18247f34ce924cb2d70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Full"}. This record does not assert independent reproduction. ### GPT-5 CIG Score: 52. Result ID: 69e5c18247f34ce924cb2d6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Summary"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro CIG Score: 52. Result ID: 69e5c18247f34ce924cb2d71. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Memory"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro CIG Score: 51.8. Result ID: 69e5c18247f34ce924cb2d73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Short Prior"}. This record does not assert independent reproduction. ### GPT-5 CIG Score: 51.2. Result ID: 69e5c18247f34ce924cb2d66. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Full"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro CIG Score: 50.5. Result ID: 69e5c18247f34ce924cb2d74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"Summary"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.