Game Playing on Balatro In-distribution seeds
24Capped Mean Final RoundDemoEvolve
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DemoEvolveSeed=B2026.05 | 24 | 3 | |
| DemoEvolveSeed=C2026.05 | 24 | 3 | |
| DemoEvolveAggregate=ID Average2026.05 | 23.33 | 8 | |
| Meta-HarnessSeed=B2026.05 | 23 | 2 | |
| BalatroLLMSeed=B2026.05 | 22 | 1 | |
| DemoEvolveSeed=A2026.05 | 22 | 2 | |
| Meta-HarnessAggregate=ID Average2026.05 | 19.33 | 4 | |
| Meta-HarnessSeed=C2026.05 | 18.3 | 2 | |
| OpenResearchSeed=C2026.05 | 17.7 | 1 | |
| OpenResearchSeed=A2026.05 | 17.3 | 0 | |
| BalatroLLMSeed=C2026.05 | 17 | 2 | |
| BalatroLLMAggregate=ID Average2026.05 | 17 | 3 | |
| Meta-HarnessSeed=A2026.05 | 16.7 | 0 | |
| OpenResearchAggregate=ID Average2026.05 | 16.67 | 2 | |
| OpenResearchSeed=B2026.05 | 15 | 1 | |
| BalatroLLMSeed=A2026.05 | 12 | 0 |