Mathematical Reasoning on GSM-Hard (Accuracy and PPD)
99AccuracyBRAID
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BRAIDGeneration Model=gpt-4o mini, Solver Model=gpt-5 medium2025.12 | 99 | 0.69 | |
| BRAIDGeneration Model=gpt-4o mini, Solver Model=gpt-5 mini medium2025.12 | 99 | 5.97 | |
| BRAIDGeneration Model=gpt-4o mini, Solver Model=gpt-5 nano medium2025.12 | 99 | 14.71 | |
| BRAIDGeneration Model=gpt-4o mini, Solver Model=gpt-5.1 medium2025.12 | 99 | 1.18 | |
| BRAIDGeneration Model=gpt-4o mini, Solver Model=gpt-5.1 none2025.12 | 99 | 2.01 | |
| BRAIDGeneration Model=gpt-5 mini medium, Solver Model=gpt-5 medium2025.12 | 99 | 0.71 | |
| BRAIDGeneration Model=gpt-5 mini medium, Solver Model=gpt-5 mini medium2025.12 | 99 | 5.96 | |
| BRAIDGeneration Model=gpt-5 mini medium, Solver Model=gpt-5 minimal2025.12 | 99 | 2.89 | |
| BRAIDGeneration Model=gpt-5 mini medium, Solver Model=gpt-5 nano medium2025.12 | 99 | 14.02 | |
| BRAIDGeneration Model=gpt-5 mini medium, Solver Model=gpt-5.1 medium2025.12 | 99 | 1.07 | |
| BRAIDGeneration Model=gpt-4.1, Solver Model=gpt-4.12025.12 | 98 | 2.67 | |
| BRAIDGeneration Model=gpt-4.1, Solver Model=gpt-5 medium2025.12 | 98 | 0.77 | |
| BRAIDGeneration Model=gpt-4.1, Solver Model=gpt-5 mini medium2025.12 | 98 | 5.77 | |
| BRAIDGeneration Model=gpt-4.1, Solver Model=gpt-5 mini minimal2025.12 | 98 | 15.62 | |
| BRAIDGeneration Model=gpt-4.1, Solver Model=gpt-5 minimal2025.12 | 98 | 3.15 | |
| BRAIDGeneration Model=gpt-4.1, Solver Model=gpt-5 nano medium2025.12 | 98 | 15.3 | |
| BRAIDGeneration Model=gpt-4.1, Solver Model=gpt-5.1 medium2025.12 | 98 | 1.22 | |
| BRAIDGeneration Model=gpt-4.1 mini, Solver Model=gpt-4.12025.12 | 98 | 2.63 | |
| BRAIDGeneration Model=gpt-4.1 mini, Solver Model=gpt-4.1 mini2025.12 | 98 | 15.18 | |
| BRAIDGeneration Model=gpt-4.1 mini, Solver Model=gpt-5 medium2025.12 | 98 | 0.77 | |
| BRAIDGeneration Model=gpt-4.1 mini, Solver Model=gpt-5 mini medium2025.12 | 98 | 6.05 | |
| BRAIDGeneration Model=gpt-4.1 mini, Solver Model=gpt-5 minimal2025.12 | 98 | 3.14 | |
| BRAIDGeneration Model=gpt-4.1 mini, Solver Model=gpt-5 nano medium2025.12 | 98 | 15.36 | |
| BRAIDGeneration Model=gpt-4.1 mini, Solver Model=gpt-5.1 medium2025.12 | 98 | 1.22 | |
| BRAIDGeneration Model=gpt-4.1 mini, Solver Model=gpt-5.1 none2025.12 | 98 | 2.21 | |
| BRAIDGeneration Model=gpt-4.1 nano, Solver Model=gpt-5.1 medium2025.12 | 98 | 1.16 | |
| BRAIDGeneration Model=gpt-4o, Solver Model=gpt-4.12025.12 | 98 | 2.64 | |
| BRAIDGeneration Model=gpt-4o, Solver Model=gpt-5 medium2025.12 | 98 | 0.8 | |
| BRAIDGeneration Model=gpt-4o, Solver Model=gpt-5 mini medium2025.12 | 98 | 6.15 | |
| BRAIDGeneration Model=gpt-4o, Solver Model=gpt-5 nano medium2025.12 | 98 | 14.73 | |
| BRAIDGeneration Model=gpt-4o, Solver Model=gpt-5.1 medium2025.12 | 98 | 1.25 | |
| BRAIDGeneration Model=gpt-4o, Solver Model=gpt-5.1 none2025.12 | 98 | 2.17 | |
| BRAIDGeneration Model=gpt-4o mini, Solver Model=gpt-5 mini minimal2025.12 | 98 | 15.18 | |
| BRAIDGeneration Model=gpt-4o mini, Solver Model=gpt-5 minimal2025.12 | 98 | 3.01 | |
| BRAIDGeneration Model=gpt-5 medium, Solver Model=gpt-5 medium2025.12 | 98 | 0.72 | |
| BRAIDGeneration Model=gpt-5 medium, Solver Model=gpt-5 mini medium2025.12 | 98 | 5.58 | |
| BRAIDGeneration Model=gpt-5 medium, Solver Model=gpt-5 mini minimal2025.12 | 98 | 14.87 | |
| BRAIDGeneration Model=gpt-5 medium, Solver Model=gpt-5 nano medium2025.12 | 98 | 14.67 | |
| BRAIDGeneration Model=gpt-5 medium, Solver Model=gpt-5.1 medium2025.12 | 98 | 1.08 | |
| BRAIDGeneration Model=gpt-5 medium, Solver Model=gpt-5.1 none2025.12 | 98 | 1.81 | |
| BRAIDGeneration Model=gpt-5 mini medium, Solver Model=gpt-4.12025.12 | 98 | 2.33 | |
| BRAIDGeneration Model=gpt-5 mini medium, Solver Model=gpt-4.1 mini2025.12 | 98 | 13.09 | |
| BRAIDGeneration Model=gpt-5 mini medium, Solver Model=gpt-5 mini minimal2025.12 | 98 | 14.38 | |
| BRAIDGeneration Model=gpt-5 mini medium, Solver Model=gpt-5.1 none2025.12 | 98 | 1.86 | |
| BRAIDGeneration Model=gpt-5 minimal, Solver Model=gpt-5 medium2025.12 | 98 | 0.72 | |
| BRAIDGeneration Model=gpt-5 minimal, Solver Model=gpt-5 mini medium2025.12 | 98 | 5.37 | |
| BRAIDGeneration Model=gpt-5 minimal, Solver Model=gpt-5 mini minimal2025.12 | 98 | 14.24 | |
| BRAIDGeneration Model=gpt-5 minimal, Solver Model=gpt-5 nano medium2025.12 | 98 | 14.47 | |
| BRAIDGeneration Model=gpt-5 minimal, Solver Model=gpt-5.1 medium2025.12 | 98 | 1.11 | |
| BRAIDGeneration Model=gpt-5 minimal, Solver Model=gpt-5.1 none2025.12 | 98 | 1.92 | |
| BRAIDGeneration Model=gpt-5 nano medium, Solver Model=gpt-5.1 medium2025.12 | 98 | 1.14 | |
| BRAIDGeneration Model=gpt-5.1 medium, Solver Model=gpt-4.12025.12 | 98 | 1.95 | |
| BRAIDGeneration Model=gpt-5.1 medium, Solver Model=gpt-5 medium2025.12 | 98 | 0.65 | |
| BRAIDGeneration Model=gpt-5.1 medium, Solver Model=gpt-5 mini medium2025.12 | 98 | 5.24 | |
| BRAIDGeneration Model=gpt-5.1 medium, Solver Model=gpt-5 mini minimal2025.12 | 98 | 11.44 | |
| BRAIDGeneration Model=gpt-5.1 medium, Solver Model=gpt-5 nano medium2025.12 | 98 | 13.21 | |
| BRAIDGeneration Model=gpt-5.1 medium, Solver Model=gpt-5 nano minimal2025.12 | 98 | 63.33 | |
| BRAIDGeneration Model=gpt-5.1 medium, Solver Model=gpt-5.1 none2025.12 | 98 | 1.73 | |
| BRAIDGeneration Model=gpt-5.1 none, Solver Model=gpt-4.12025.12 | 98 | 1.84 | |
| BRAIDGeneration Model=gpt-5.1 none, Solver Model=gpt-5 medium2025.12 | 98 | 0.55 | |
| BRAIDGeneration Model=gpt-5.1 none, Solver Model=gpt-5 mini medium2025.12 | 98 | 4.83 | |
| BRAIDGeneration Model=gpt-5.1 none, Solver Model=gpt-5 mini minimal2025.12 | 98 | 10.67 | |
| BRAIDGeneration Model=gpt-5.1 none, Solver Model=gpt-5 nano medium2025.12 | 98 | 14.32 | |
| BRAIDGeneration Model=gpt-5.1 none, Solver Model=gpt-5 nano minimal2025.12 | 98 | 61.54 | |
| BRAIDGeneration Model=gpt-5.1 none, Solver Model=gpt-5.1 none2025.12 | 98 | 1.61 | |
| BRAIDGeneration Model=gpt-4.1, Solver Model=gpt-4.1 mini2025.12 | 97 | 14.86 | |
| BRAIDGeneration Model=gpt-4.1, Solver Model=gpt-4o2025.12 | 97 | 1.68 | |
| BRAIDGeneration Model=gpt-4.1, Solver Model=gpt-5.1 none2025.12 | 97 | 2.26 | |
| BRAIDGeneration Model=gpt-4.1 mini, Solver Model=gpt-5 mini minimal2025.12 | 97 | 15.92 | |
| BRAIDGeneration Model=gpt-4.1 nano, Solver Model=gpt-5 medium2025.12 | 97 | 0.68 | |
| BRAIDGeneration Model=gpt-4.1 nano, Solver Model=gpt-5 mini medium2025.12 | 97 | 5.52 | |
| BRAIDGeneration Model=gpt-4.1 nano, Solver Model=gpt-5 nano medium2025.12 | 97 | 13.54 | |
| BRAIDGeneration Model=gpt-4.1 nano, Solver Model=gpt-5.1 none2025.12 | 97 | 2.25 | |
| BRAIDGeneration Model=gpt-4o, Solver Model=gpt-4o2025.12 | 97 | 1.65 | |
| BRAIDGeneration Model=gpt-4o, Solver Model=gpt-5 minimal2025.12 | 97 | 3.29 | |
| BRAIDGeneration Model=gpt-4o mini, Solver Model=gpt-4.12025.12 | 97 | 2.48 | |
| BRAIDGeneration Model=gpt-4o mini, Solver Model=gpt-5 nano minimal2025.12 | 97 | 69.15 | |
| BRAIDGeneration Model=gpt-5 medium, Solver Model=gpt-4.12025.12 | 97 | 2.35 | |
| BRAIDGeneration Model=gpt-5 medium, Solver Model=gpt-4.1 mini2025.12 | 97 | 13.04 | |
| BRAIDGeneration Model=gpt-5 medium, Solver Model=gpt-5 minimal2025.12 | 97 | 2.96 | |
| BRAIDGeneration Model=gpt-5 minimal, Solver Model=gpt-4o2025.12 | 97 | 1.56 | |
| BRAIDGeneration Model=gpt-5 nano medium, Solver Model=gpt-5 medium2025.12 | 97 | 0.74 | |
| BRAIDGeneration Model=gpt-5 nano medium, Solver Model=gpt-5 mini medium2025.12 | 97 | 5.6 | |
| BRAIDGeneration Model=gpt-5 nano medium, Solver Model=gpt-5.1 none2025.12 | 97 | 2.04 | |
| BRAIDGeneration Model=gpt-5.1 medium, Solver Model=gpt-4.1 mini2025.12 | 97 | 11.34 | |
| BRAIDGeneration Model=gpt-5.1 medium, Solver Model=gpt-5 minimal2025.12 | 97 | 2.29 | |
| BRAIDGeneration Model=gpt-5.1 medium, Solver Model=gpt-5.1 medium2025.12 | 97 | 0.97 | |
| BRAIDGeneration Model=gpt-5.1 none, Solver Model=gpt-4.1 mini2025.12 | 97 | 10.74 | |
| BRAIDGeneration Model=gpt-5.1 none, Solver Model=gpt-5 minimal2025.12 | 97 | 2.13 | |
| BRAIDGeneration Model=gpt-5.1 none, Solver Model=gpt-5.1 medium2025.12 | 97 | 0.8 | |
| BRAIDGeneration Model=gpt-4.1, Solver Model=gpt-5 nano minimal2025.12 | 96 | 74.06 | |
| BRAIDGeneration Model=gpt-4.1 nano, Solver Model=gpt-4.12025.12 | 96 | 2.51 | |
| BRAIDGeneration Model=gpt-4.1 nano, Solver Model=gpt-5 mini minimal2025.12 | 96 | 15.11 | |
| BRAIDGeneration Model=gpt-4.1 nano, Solver Model=gpt-5 minimal2025.12 | 96 | 3.06 | |
| BRAIDGeneration Model=gpt-4o, Solver Model=gpt-4.1 mini2025.12 | 96 | 14.78 | |
| BRAIDGeneration Model=gpt-4o, Solver Model=gpt-5 mini minimal2025.12 | 96 | 15.41 | |
| BRAIDGeneration Model=gpt-4o mini, Solver Model=gpt-4o2025.12 | 96 | 1.54 | |
| BRAIDGeneration Model=gpt-5 medium, Solver Model=gpt-5 nano minimal2025.12 | 96 | 64.56 | |
| BRAIDGeneration Model=gpt-5 mini medium, Solver Model=gpt-5 nano minimal2025.12 | 96 | 63.77 | |
| BRAIDGeneration Model=gpt-5 mini minimal, Solver Model=gpt-4.12025.12 | 96 | 2.24 |