# Retrosynthesis on Mol-Instructions (test)

Source: [Retrosynthesis on Mol-Instructions (test)](<https://www.sota2.com/research/sota/retrosynthesis-on-mol-instructions-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:41:43.540Z

Evaluation of models performing retrosynthesis prediction on the test split of the Mol-Instructions dataset, measured using metrics like EM score, BLEU, METEOR, and validity checks.

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 | Retrosynthesis |
| Dataset (including any stated split) | Mol-Instructions (test) |
| Metric | EM Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [EM Score](<https://www.sota2.com/research/sota/retrosynthesis-on-mol-instructions-test.md?metric=EM%20Score>): Higher is better; unit: SCALAR.

- [BLEU Score](<https://www.sota2.com/research/sota/retrosynthesis-on-mol-instructions-test.md?metric=BLEU%20Score>): Higher is better; unit: SCALAR.

- [METEOR Score](<https://www.sota2.com/research/sota/retrosynthesis-on-mol-instructions-test.md?metric=METEOR%20Score>): Higher is better; unit: SCALAR.

- [Similarity Score](<https://www.sota2.com/research/sota/retrosynthesis-on-mol-instructions-test.md?metric=Similarity%20Score>): Higher is better; unit: SCALAR.

- [Validity Score](<https://www.sota2.com/research/sota/retrosynthesis-on-mol-instructions-test.md?metric=Validity%20Score>): Higher is better; unit: PERCENT.

- [Improvement Metric](<https://www.sota2.com/research/sota/retrosynthesis-on-mol-instructions-test.md?metric=Improvement%20Metric>): Higher is better; unit: SCALAR.

## Recorded results

| Method | EM Score | Result date | Report paper |
| --- | --- | --- | --- |
| LLM-CRP | 0.757 | Not recorded | 68fa5f581e209131ce9e9189 |
| LLM-CRP | 0.749 | Not recorded | 68fa5f581e209131ce9e9189 |
| Text+Chem T5 | 0.663 | Not recorded | 68fa5f581e209131ce9e9189 |
| LLM-CRP | 0.654 | Not recorded | 68fa5f581e209131ce9e9189 |
| T5 | 0.649 | Not recorded | 68fa5f581e209131ce9e9189 |
| MolT5 | 0.637 | Not recorded | 68fa5f581e209131ce9e9189 |
| nach0 | 0.39 | Not recorded | 68fa5f581e209131ce9e9189 |
| Text+Chem T5 | 0.372 | Not recorded | 68fa5f581e209131ce9e9189 |

### LLM-CRP

EM Score: 0.757. Result ID: 698bc4097a967eddb77131bf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e9189.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e9189.md>)

[Implementation](<https://github.com/AI-HPC-Research-Team/SLM4CRP>)

Recorded evaluation configuration: {"RT":true,"IA":true,"N":10}. This record does not assert independent reproduction.

### LLM-CRP

EM Score: 0.749. Result ID: 698bc4097a967eddb77131be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e9189.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e9189.md>)

[Implementation](<https://github.com/AI-HPC-Research-Team/SLM4CRP>)

Recorded evaluation configuration: {"RT":true,"IA":false,"N":10}. This record does not assert independent reproduction.

### Text+Chem T5

EM Score: 0.663. Result ID: 698bc4097a967eddb77131bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e9189.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f711e209131cea459c6.md>)

[Implementation](<https://github.com/GT4SD/multitask_text_and_chemistry_t5>)

Recorded evaluation configuration: {"finetuned":true}. This record does not assert independent reproduction.

### LLM-CRP

EM Score: 0.654. Result ID: 698bc4097a967eddb77131c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e9189.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e9189.md>)

[Implementation](<https://github.com/AI-HPC-Research-Team/SLM4CRP>)

Recorded evaluation configuration: {"RT":true,"IA":true,"N":6}. This record does not assert independent reproduction.

### T5

EM Score: 0.649. Result ID: 698bc4097a967eddb77131bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e9189.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"finetuned":true}. This record does not assert independent reproduction.

### MolT5

EM Score: 0.637. Result ID: 698bc4097a967eddb77131bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e9189.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dde1e209131cea3c90f.md>)

[Implementation](<https://github.com/blender-nlp/MolT5>)

Recorded evaluation configuration: {"finetuned":true}. This record does not assert independent reproduction.

### nach0

EM Score: 0.39. Result ID: 698bc4097a967eddb77131ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e9189.md>)

Recorded evaluation configuration: {"finetuned":false}. This record does not assert independent reproduction.

### Text+Chem T5

EM Score: 0.372. Result ID: 698bc4097a967eddb77131b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e9189.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f711e209131cea459c6.md>)

[Implementation](<https://github.com/GT4SD/multitask_text_and_chemistry_t5>)

Recorded evaluation configuration: {"finetuned":false}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.