# System-level Correlation with Human Judgment on MS COCO M1 (system-level) Source: [System-level Correlation with Human Judgment on MS COCO M1 (system-level)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:57:44.350Z Evaluation of model performance based on system-level correlation with human judgments using the MS COCO M1 dataset variant, typically measured using Pearson's r. 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 | System-level Correlation with Human Judgment | | Dataset (including any stated split) | MS COCO M1 (system-level) | | Metric | Pearson r | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [Pearson r](): Higher is better; unit: SCALAR. - [P-Value](): Lower is better; unit: SCALAR. ## Recorded results | Method | Pearson r | Result date | Report paper | | --- | --- | --- | --- | | BERTScore | 0.986 | Not recorded | 68fa6b991e209131cea2f2c0 | | SMURF | 0.984 | Not recorded | 68fa6b991e209131cea2f2c0 | | SPICE | 0.956 | Not recorded | 68fa6b991e209131cea2f2c0 | | SPURTS | 0.956 | Not recorded | 68fa6b991e209131cea2f2c0 | | SPARCS | 0.874 | Not recorded | 68fa6b991e209131cea2f2c0 | | METEOR | 0.479 | Not recorded | 68fa6b991e209131cea2f2c0 | | BS-w/oidf | 0.374 | Not recorded | 68fa6b991e209131cea2f2c0 | | CIDEr | 0.023 | Not recorded | 68fa6b991e209131cea2f2c0 | | Bleu-1 | -0.279 | Not recorded | 68fa6b991e209131cea2f2c0 | | Bleu-2 | -0.709 | Not recorded | 68fa6b991e209131cea2f2c0 | | Rouge-L | -0.812 | Not recorded | 68fa6b991e209131cea2f2c0 | ### BERTScore Pearson r: 0.986. Result ID: 698e9868ffc3901de09ef9bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SMURF Pearson r: 0.984. Result ID: 698e9868ffc3901de09ef9c9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SPICE Pearson r: 0.956. Result ID: 698e9868ffc3901de09ef9c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SPURTS Pearson r: 0.956. Result ID: 698e9868ffc3901de09ef9c8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SPARCS Pearson r: 0.874. Result ID: 698e9868ffc3901de09ef9c7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### METEOR Pearson r: 0.479. Result ID: 698e9868ffc3901de09ef9c4. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BS-w/oidf Pearson r: 0.374. Result ID: 698e9868ffc3901de09ef9c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CIDEr Pearson r: 0.023. Result ID: 698e9868ffc3901de09ef9c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Bleu-1 Pearson r: -0.279. Result ID: 698e9868ffc3901de09ef9c1. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Bleu-2 Pearson r: -0.709. Result ID: 698e9868ffc3901de09ef9c2. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Rouge-L Pearson r: -0.812. Result ID: 698e9868ffc3901de09ef9c3. [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.