Randomized Symbolic Reduction on RSR-BENCH Algebraic Structures v1.0 (17 functions)
170RSR CountClaude-Opus-4.1
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Claude-Opus-4.1Framework=A-BITWEEN2024.12 | 170 | 371 | 0 | 100 | 238 | 378 | 554 | |
| Claude-Sonnet-4Framework=A-BITWEEN2024.12 | 139 | 294 | 0 | 94 | 81 | 114 | 160 | |
| Claude-Opus-4.1Framework=N-RESEARCH2024.12 | 107 | 203 | 8 | 100 | 174 | 269 | 363 | |
| GPT-OSS-120BFramework=N-RESEARCH2024.12 | 79 | 121 | 3 | 88 | 6 | 14 | 31 | |
| GPT-OSS-120BFramework=A-BITWEEN2024.12 | 79 | 105 | 0 | 100 | 8 | 16 | 41 | |
| Claude-Sonnet-4Framework=N-RESEARCH2024.12 | 76 | 134 | 7 | 88 | 46 | 64 | 99 | |
| PySRFramework=V-BITWEEN2024.12 | 12 | 16 | 6 | 65 | 7 | 60 | 306 | |
| GPLearnFramework=V-BITWEEN2024.12 | 12 | 17 | 6 | 65 | 0 | 54 | 344 | |
| MILPFramework=V-BITWEEN2024.12 | 12 | 16 | 0 | 65 | 0 | 2 | 9 | |
| LRFramework=V-BITWEEN2024.12 | 12 | 16 | 0 | 65 | 0 | 1 | 6 |