# Opponent Exploitation on Leduc Hold'em (3k hands, paired seeds, held-out)

Source: [Opponent Exploitation on Leduc Hold'em (3k hands, paired seeds, held-out)](<https://www.sota2.com/research/sota/opponent-exploitation-on-leduc-hold-em-3k-hands-paired-seeds-held-out>)

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

Data updated: 2026-04-29T06:41:34.738Z

Evaluation of agent performance in Leduc Hold'em focusing on opponent exploitation, using metrics like Model EV, GTO EV, and Gain, based on a held-out test set configuration of 3,000 hands across 3 trials with paired seeds.

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 | Opponent Exploitation |
| Dataset (including any stated split) | Leduc Hold'em 3,000 hands × 3 trials, paired seeds (Held-out) |
| Metric | Gain |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Gain](<https://www.sota2.com/research/sota/opponent-exploitation-on-leduc-hold-em-3k-hands-paired-seeds-held-out.md?metric=Gain>): Higher is better; unit: SCALAR.

- [Model EV](<https://www.sota2.com/research/sota/opponent-exploitation-on-leduc-hold-em-3k-hands-paired-seeds-held-out.md?metric=Model%20EV>): Higher is better; unit: SCALAR.

- [GTO EV](<https://www.sota2.com/research/sota/opponent-exploitation-on-leduc-hold-em-3k-hands-paired-seeds-held-out.md?metric=GTO%20EV>): Higher is better; unit: SCALAR.

- [95% CI](<https://www.sota2.com/research/sota/opponent-exploitation-on-leduc-hold-em-3k-hands-paired-seeds-held-out.md?metric=95%25%20CI>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Gain | Result date | Report paper |
| --- | --- | --- | --- |
| StratFormer | 0.821 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | 0.193 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | 0.173 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | 0.139 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | 0.106 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | 0.084 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | 0.071 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | 0.046 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | 0.013 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | -0.02 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | -0.021 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | -0.05 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | -0.058 | Not recorded | 69f190c655a3c32af89fbcd7 |
| StratFormer | -0.171 | Not recorded | 69f190c655a3c32af89fbcd7 |

### StratFormer

Gain: 0.821. Result ID: 69f1a63747f34ce924d796ff.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"maniac\_high","Opponent Exploitability (ε)":"1.26"}. This record does not assert independent reproduction.

### StratFormer

Gain: 0.193. Result ID: 69f1a63747f34ce924d796fe.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"loose\_agg\_high","Opponent Exploitability (ε)":"0.60"}. This record does not assert independent reproduction.

### StratFormer

Gain: 0.173. Result ID: 69f1a63747f34ce924d796fa.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"maniac\_mid","Opponent Exploitability (ε)":"0.46"}. This record does not assert independent reproduction.

### StratFormer

Gain: 0.139. Result ID: 69f1a63747f34ce924d796f8.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"passive\_high","Opponent Exploitability (ε)":"0.33"}. This record does not assert independent reproduction.

### StratFormer

Gain: 0.106. Result ID: 69f1a63747f34ce924d79700.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"Average (excl. GTO)"}. This record does not assert independent reproduction.

### StratFormer

Gain: 0.084. Result ID: 69f1a63747f34ce924d796fb.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"nit\_high","Opponent Exploitability (ε)":"0.48"}. This record does not assert independent reproduction.

### StratFormer

Gain: 0.071. Result ID: 69f1a63747f34ce924d796f7.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"tight\_passive\_mid","Opponent Exploitability (ε)":"0.33"}. This record does not assert independent reproduction.

### StratFormer

Gain: 0.046. Result ID: 69f1a63747f34ce924d796fd.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"tight\_passive\_high","Opponent Exploitability (ε)":"0.53"}. This record does not assert independent reproduction.

### StratFormer

Gain: 0.013. Result ID: 69f1a63747f34ce924d796fc.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"over\_caller\_high","Opponent Exploitability (ε)":"0.53"}. This record does not assert independent reproduction.

### StratFormer

Gain: -0.02. Result ID: 69f1a63747f34ce924d796f6.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"loose\_agg\_mid","Opponent Exploitability (ε)":"0.25"}. This record does not assert independent reproduction.

### StratFormer

Gain: -0.021. Result ID: 69f1a63747f34ce924d796f9.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"nit\_mid","Opponent Exploitability (ε)":"0.34"}. This record does not assert independent reproduction.

### StratFormer

Gain: -0.05. Result ID: 69f1a63747f34ce924d796f3.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"GTO","Opponent Exploitability (ε)":"0.00"}. This record does not assert independent reproduction.

### StratFormer

Gain: -0.058. Result ID: 69f1a63747f34ce924d796f4.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"passive\_mid","Opponent Exploitability (ε)":"0.15"}. This record does not assert independent reproduction.

### StratFormer

Gain: -0.171. Result ID: 69f1a63747f34ce924d796f5.

[Reporting paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f190c655a3c32af89fbcd7.md>)

Recorded evaluation configuration: {"Opponent":"over\_caller\_mid","Opponent Exploitability (ε)":"0.23"}. This record does not assert independent reproduction.

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