# Mutation Fitness Prediction on ProteinGym Source: [Mutation Fitness Prediction on ProteinGym]() Collection index: [llms.txt]() Data updated: 2026-04-15T07:52:18.198Z Evaluation of model performance on predicting mutation fitness within the ProteinGym dataset, typically measured using classification metrics like AUROC. 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 | Mutation Fitness Prediction | | Dataset (including any stated split) | ProteinGym | | Metric | AUROC | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [AUROC](): Higher is better; unit: PERCENT. ## Recorded results | Method | AUROC | Result date | Report paper | | --- | --- | --- | --- | | TriFit | 89.74 | Not recorded | 69df1b9c7d0172140ec7b967 | | ESM3 | 76.92 | Not recorded | 69df1b9c7d0172140ec7b967 | | SaProt-650M | 75.93 | Not recorded | 69df1b9c7d0172140ec7b967 | | GEMME | 75.65 | Not recorded | 69df1b9c7d0172140ec7b967 | | VESPA | 75.64 | Not recorded | 69df1b9c7d0172140ec7b967 | | TranceptEVE L | 75.49 | Not recorded | 69df1b9c7d0172140ec7b967 | | ESM2-650M | 74.43 | Not recorded | 69df1b9c7d0172140ec7b967 | | ESM-IF1 | 74.42 | Not recorded | 69df1b9c7d0172140ec7b967 | | MSA Transformer (ensemble) | 74.3 | Not recorded | 69df1b9c7d0172140ec7b967 | | Tranception L | 74.14 | Not recorded | 69df1b9c7d0172140ec7b967 | | ESM1v (ensemble) | 73.12 | Not recorded | 69df1b9c7d0172140ec7b967 | | ESM1b | 72.12 | Not recorded | 69df1b9c7d0172140ec7b967 | | ESM1v | 71.66 | Not recorded | 69df1b9c7d0172140ec7b967 | | EVmutation | 71.65 | Not recorded | 69df1b9c7d0172140ec7b967 | | Site Independent | 69.67 | Not recorded | 69df1b9c7d0172140ec7b967 | | ProteinMPNN | 65.32 | Not recorded | 69df1b9c7d0172140ec7b967 | ### TriFit AUROC: 89.74. Result ID: 69df426447f34ce924c7c3d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Supervised"}. This record does not assert independent reproduction. ### ESM3 AUROC: 76.92. Result ID: 69df426447f34ce924c7c3d7. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### SaProt-650M AUROC: 75.93. Result ID: 69df426447f34ce924c7c3d6. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### GEMME AUROC: 75.65. Result ID: 69df426447f34ce924c7c3d4. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### VESPA AUROC: 75.64. Result ID: 69df426447f34ce924c7c3d3. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### TranceptEVE L AUROC: 75.49. Result ID: 69df426447f34ce924c7c3d2. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### ESM2-650M AUROC: 74.43. Result ID: 69df426447f34ce924c7c3cf. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### ESM-IF1 AUROC: 74.42. Result ID: 69df426447f34ce924c7c3d5. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### MSA Transformer (ensemble) AUROC: 74.3. Result ID: 69df426447f34ce924c7c3d0. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### Tranception L AUROC: 74.14. Result ID: 69df426447f34ce924c7c3d1. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### ESM1v (ensemble) AUROC: 73.12. Result ID: 69df426447f34ce924c7c3ce. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### ESM1b AUROC: 72.12. Result ID: 69df426447f34ce924c7c3cc. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### ESM1v AUROC: 71.66. Result ID: 69df426447f34ce924c7c3cd. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### EVmutation AUROC: 71.65. Result ID: 69df426447f34ce924c7c3cb. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### Site Independent AUROC: 69.67. Result ID: 69df426447f34ce924c7c3c9. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot"}. This record does not assert independent reproduction. ### ProteinMPNN AUROC: 65.32. Result ID: 69df426447f34ce924c7c3ca. [Reporting paper]() 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.