Single-cell Denoising on PBMC OpenProblems benchmark
0.711Mean ScoreAster
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Asteriterations=302026.02 | 0.711 | 0.15 | 0.049 | |
| TTT-DiscoverModel=gpt-oss-120b2026.01 | 0.71 | 0.15 | 0.05 | |
| TTT-Discover2026.02 | 0.709 | 0.154 | 0.048 | |
| OpenEvolveModel=gpt-oss-120b2026.01 | 0.7 | 0.16 | 0.05 | |
| Best Human (MAGIC)2026.02 | 0.641 | 0.19 | 0.05 | |
| MAGIC (A, R)2026.01 | 0.64 | 0.19 | 0.05 | |
| MAGIC (R)2026.01 | 0.64 | 0.19 | 0.05 | |
| Best-of-25600Model=gpt-oss-120b2026.01 | 0.62 | 0.2 | 0.05 | |
| ALRA (S, RN)2026.01 | 0.5 | 0.26 | 0.05 | |
| MAGIC (A)2026.01 | 0.42 | 0.19 | 0.16 | |
| MAGIC2026.01 | 0.42 | 0.19 | 0.16 |