# Symbolic Regression on LLM-SRBench matsci Source: [Symbolic Regression on LLM-SRBench matsci]() Collection index: [llms.txt]() Data updated: 2026-05-18T06:47:37.449Z Evaluation of Symbolic Regression performance on the Material Science subset of the LLM-SRBench dataset, reporting metrics such as Best reward and LLM calls. 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 | Symbolic Regression | | Dataset (including any stated split) | LLM-SRBench matsci | | Metric | Best Reward | | Unit | SCALAR | | 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 - [Best Reward](): Higher is better; unit: SCALAR. - [LLM Calls](): Lower is better; unit: SCALAR. ## Recorded results | Method | Best Reward | Result date | Report paper | | --- | --- | --- | --- | | SMCEVOLVE | 8.25 | Not recorded | 6a0a9d0adbc836b87d82b376 | | OPENEVOLVE | 6.9586 | Not recorded | 6a0a9d0adbc836b87d82b376 | | SHINKAEVOLVE | 6.0224 | Not recorded | 6a0a9d0adbc836b87d82b376 | | SMCEVOLVE | 5.5511 | Not recorded | 6a0a9d0adbc836b87d82b376 | | OPENEVOLVE | 4.567 | Not recorded | 6a0a9d0adbc836b87d82b376 | | REEVO | 4.4763 | Not recorded | 6a0a9d0adbc836b87d82b376 | | SMCEVOLVE | 4.4687 | Not recorded | 6a0a9d0adbc836b87d82b376 | | SHINKAEVOLVE | 4.279 | Not recorded | 6a0a9d0adbc836b87d82b376 | | REEVO | 3.8771 | Not recorded | 6a0a9d0adbc836b87d82b376 | | SHINKAEVOLVE | 3.1858 | Not recorded | 6a0a9d0adbc836b87d82b376 | | OPENEVOLVE | 3.0537 | Not recorded | 6a0a9d0adbc836b87d82b376 | | REEVO | 1.4764 | Not recorded | 6a0a9d0adbc836b87d82b376 | | SMCEVOLVE | 0.1522 | Not recorded | 6a0a9d0adbc836b87d82b376 | | SHINKAEVOLVE | 0.1521 | Not recorded | 6a0a9d0adbc836b87d82b376 | | OPENEVOLVE | 0.152 | Not recorded | 6a0a9d0adbc836b87d82b376 | | REEVO | 0.1518 | Not recorded | 6a0a9d0adbc836b87d82b376 | ### SMCEVOLVE Best Reward: 8.25. Result ID: 6a0ab48947f34ce924f03602. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task":"MatSci2"}. This record does not assert independent reproduction. ### OPENEVOLVE Best Reward: 6.9586. Result ID: 6a0ab48947f34ce924f03600. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task":"MatSci2"}. This record does not assert independent reproduction. ### SHINKAEVOLVE Best Reward: 6.0224. Result ID: 6a0ab48947f34ce924f03601. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task":"MatSci2"}. This record does not assert independent reproduction. ### SMCEVOLVE Best Reward: 5.5511. Result ID: 6a0ab48947f34ce924f035fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task":"MatSci0"}. This record does not assert independent reproduction. ### OPENEVOLVE Best Reward: 4.567. Result ID: 6a0ab48947f34ce924f035f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task":"MatSci0"}. This record does not assert independent reproduction. ### REEVO Best Reward: 4.4763. Result ID: 6a0ab48947f34ce924f035ff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Task":"MatSci2"}. This record does not assert independent reproduction. ### SMCEVOLVE Best Reward: 4.4687. Result ID: 6a0ab48947f34ce924f03606. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task":"MatSci3"}. This record does not assert independent reproduction. ### SHINKAEVOLVE Best Reward: 4.279. Result ID: 6a0ab48947f34ce924f035f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task":"MatSci0"}. This record does not assert independent reproduction. ### REEVO Best Reward: 3.8771. Result ID: 6a0ab48947f34ce924f035f7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Task":"MatSci0"}. This record does not assert independent reproduction. ### SHINKAEVOLVE Best Reward: 3.1858. Result ID: 6a0ab48947f34ce924f03605. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task":"MatSci3"}. This record does not assert independent reproduction. ### OPENEVOLVE Best Reward: 3.0537. Result ID: 6a0ab48947f34ce924f03604. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task":"MatSci3"}. This record does not assert independent reproduction. ### REEVO Best Reward: 1.4764. Result ID: 6a0ab48947f34ce924f03603. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Task":"MatSci3"}. This record does not assert independent reproduction. ### SMCEVOLVE Best Reward: 0.1522. Result ID: 6a0ab48947f34ce924f035fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task":"MatSci1"}. This record does not assert independent reproduction. ### SHINKAEVOLVE Best Reward: 0.1521. Result ID: 6a0ab48947f34ce924f035fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task":"MatSci1"}. This record does not assert independent reproduction. ### OPENEVOLVE Best Reward: 0.152. Result ID: 6a0ab48947f34ce924f035fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task":"MatSci1"}. This record does not assert independent reproduction. ### REEVO Best Reward: 0.1518. Result ID: 6a0ab48947f34ce924f035fb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Task":"MatSci1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.