# Presentation Solving on Miller–Schupp benchmark 1190-presentation

Source: [Presentation Solving on Miller–Schupp benchmark 1190-presentation](<https://www.sota2.com/research/sota/presentation-solving-on-miller-schupp-benchmark-1190-presentation>)

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

Data updated: 2026-06-23T09:23:23.222Z

Evaluation of model performance on the Miller–Schupp benchmark 1190-presentation dataset, focusing on the ability to solve presentations.

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 | Presentation Solving |
| Dataset (including any stated split) | Miller–Schupp benchmark 1190-presentation |
| Metric | Presentations Solved |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [Presentations Solved](<https://www.sota2.com/research/sota/presentation-solving-on-miller-schupp-benchmark-1190-presentation.md?metric=Presentations%20Solved>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Presentations Solved | Result date | Report paper |
| --- | --- | --- | --- |
| GS-SUB (1M) NODES | 640 | Not recorded | 6a3a134e206542251d7c72a8 |
| GS-SUB (10M) NODES | 640 | Not recorded | 6a3a134e206542251d7c72a8 |
| GS-SUB (100K) NODES | 634 | Not recorded | 6a3a134e206542251d7c72a8 |
| PPO-SUB-DRT + AC-19 | 607.2 | Not recorded | 6a3a134e206542251d7c72a8 |
| PPO-SUB-DRT + AC-1M | 605.4 | Not recorded | 6a3a134e206542251d7c72a8 |
| GS-SUB (10K) NODES | 604 | Not recorded | 6a3a134e206542251d7c72a8 |
| PPO-SUB-DRT | 588.2 | Not recorded | 6a3a134e206542251d7c72a8 |
| PPO-SUB-CANON + AC-19 | 575.5 | Not recorded | 6a3a134e206542251d7c72a8 |
| PPO-SUB-CANON | 562.6 | Not recorded | 6a3a134e206542251d7c72a8 |
| GS-AC (1M) | 533 | Not recorded | 6a3a134e206542251d7c72a8 |
| GS-SUB (614) | 533 | Not recorded | 6a3a134e206542251d7c72a8 |
| PPO-AC-RESNET | 457 | Not recorded | 6a3a134e206542251d7c72a8 |

### GS-SUB (1M) NODES

Presentations Solved: 640. Result ID: 6a3a507bfbc373592c35b48a.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

Recorded evaluation configuration: {"Search Algorithm":"Greedy Search","Move Set":"Substitution supermoves","Search Budget (Nodes)":"1M"}. This record does not assert independent reproduction.

### GS-SUB (10M) NODES

Presentations Solved: 640. Result ID: 6a3a507bfbc373592c35b48b.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

Recorded evaluation configuration: {"Search Algorithm":"Greedy Search","Move Set":"Substitution supermoves","Search Budget (Nodes)":"10M"}. This record does not assert independent reproduction.

### GS-SUB (100K) NODES

Presentations Solved: 634. Result ID: 6a3a507bfbc373592c35b489.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

Recorded evaluation configuration: {"Search Algorithm":"Greedy Search","Move Set":"Substitution supermoves","Search Budget (Nodes)":"100K"}. This record does not assert independent reproduction.

### PPO-SUB-DRT + AC-19

Presentations Solved: 607.2. Result ID: 6a3a507bfbc373592c35b485.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

Recorded evaluation configuration: {"Search Algorithm":"PPO","Move Set":"Substitution supermoves","Model Architecture":"Dual-Ring Transformer","Additional Training Data":"AC-19"}. This record does not assert independent reproduction.

### PPO-SUB-DRT + AC-1M

Presentations Solved: 605.4. Result ID: 6a3a507bfbc373592c35b484.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

Recorded evaluation configuration: {"Search Algorithm":"PPO","Move Set":"Substitution supermoves","Model Architecture":"Dual-Ring Transformer","Additional Training Data":"AC-1M"}. This record does not assert independent reproduction.

### GS-SUB (10K) NODES

Presentations Solved: 604. Result ID: 6a3a507bfbc373592c35b488.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

Recorded evaluation configuration: {"Search Algorithm":"Greedy Search","Move Set":"Substitution supermoves","Search Budget (Nodes)":"10K"}. This record does not assert independent reproduction.

### PPO-SUB-DRT

Presentations Solved: 588.2. Result ID: 6a3a507bfbc373592c35b483.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

Recorded evaluation configuration: {"Search Algorithm":"PPO","Move Set":"Substitution supermoves","Model Architecture":"Dual-Ring Transformer","Preprocessing Strategy":"cyclic relative positional encodings"}. This record does not assert independent reproduction.

### PPO-SUB-CANON + AC-19

Presentations Solved: 575.5. Result ID: 6a3a507bfbc373592c35b482.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

Recorded evaluation configuration: {"Search Algorithm":"PPO","Move Set":"Substitution supermoves","Preprocessing Strategy":"canonical form preprocessing","Additional Training Data":"AC-19"}. This record does not assert independent reproduction.

### PPO-SUB-CANON

Presentations Solved: 562.6. Result ID: 6a3a507bfbc373592c35b481.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

Recorded evaluation configuration: {"Search Algorithm":"PPO","Move Set":"Substitution supermoves","Preprocessing Strategy":"canonical form preprocessing"}. This record does not assert independent reproduction.

### GS-AC (1M)

Presentations Solved: 533. Result ID: 6a3a507bfbc373592c35b486.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5cff1e209131ce9d60ba.md>)

Recorded evaluation configuration: {"Search Algorithm":"Greedy Search","Move Set":"AC-moves","Search Budget (Nodes)":"1M"}. This record does not assert independent reproduction.

### GS-SUB (614)

Presentations Solved: 533. Result ID: 6a3a507bfbc373592c35b487.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

Recorded evaluation configuration: {"Search Algorithm":"Greedy Search","Move Set":"Substitution supermoves","Search Budget (Nodes)":"614"}. This record does not assert independent reproduction.

### PPO-AC-RESNET

Presentations Solved: 457. Result ID: 6a3a507bfbc373592c35b480.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5cff1e209131ce9d60ba.md>)

Recorded evaluation configuration: {"Search Algorithm":"PPO","Move Set":"AC-moves","Model Architecture":"ResNet"}. This record does not assert independent reproduction.

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