{
    "DeepSeekMath-Base": {
        "OCWCourses": {
            "cot": {
                "accuracy": 0.15441176470588236,
                "n_samples": 272
            },
            "tool": {
                "n_samples": 0
            }
        },
        "cmath-cot-test": {
            "cot": {
                "accuracy": 0.7167577413479053,
                "n_samples": 1098
            },
            "tool": {
                "n_samples": 0
            }
        },
        "miniF2F-Isabelle-test": {
            "cot": {
                "accuracy": 1.0,
                "n_samples": 244
            },
            "tool": {
                "n_samples": 0
            }
        },
        "gsm8k-cot-test": {
            "cot": {
                "accuracy": 0.6421531463229719,
                "n_samples": 1319
            },
            "tool": {
                "n_samples": 0
            }
        },
        "MMLU-STEM-test": {
            "cot": {
                "accuracy": 0.5646123260437376,
                "n_samples": 3018
            },
            "tool": {
                "n_samples": 0
            }
        },
        "agieval-gaokao-mathqa-cot-test": {
            "cot": {
                "accuracy": 0.35327635327635326,
                "n_samples": 351
            },
            "tool": {
                "n_samples": 0
            }
        },
        "agieval-gaokao-mathcloze-cot-test": {
            "cot": {
                "accuracy": 0.2033898305084746,
                "n_samples": 118
            },
            "tool": {
                "n_samples": 0
            }
        },
        "gsm8k-pal-test": {
            "cot": {
                "n_samples": 0
            },
            "tool": {
                "accuracy": 0.66868840030326,
                "n_samples": 1319
            }
        },
        "math_sat": {
            "cot": {
                "accuracy": 0.84375,
                "n_samples": 32
            },
            "tool": {
                "n_samples": 0
            }
        },
        "miniF2F-Isabelle-valid": {
            "cot": {
                "accuracy": 1.0,
                "n_samples": 244
            },
            "tool": {
                "n_samples": 0
            }
        },
        "math-pal-test": {
            "cot": {
                "n_samples": 0
            },
            "tool": {
                "accuracy": 0.3142,
                "n_samples": 5000
            }
        },
        "math-cot-test": {
            "cot": {
                "accuracy": 0.3618,
                "n_samples": 5000
            },
            "tool": {
                "n_samples": 0
            }
        }
    },
    "DeepSeekMath-RL": {
        "mgsm-zh": {
            "cot": {
                "accuracy": 0.796,
                "n_samples": 250
            },
            "tool": {
                "accuracy": 0.784,
                "program_accuracy": 0.776,
                "n_samples": 250
            }
        },
        "cmath": {
            "cot": {
                "accuracy": 0.8879781420765027,
                "n_samples": 1098
            },
            "tool": {
                "accuracy": 0.8761384335154827,
                "program_accuracy": 0.8570127504553734,
                "n_samples": 1098
            }
        },
        "math-test": {
            "cot": {
                "accuracy": 0.517,
                "n_samples": 5000
            },
            "tool": {
                "accuracy": 0.5878,
                "program_accuracy": 0.509,
                "n_samples": 5000
            }
        },
        "gsm8k-test": {
            "cot": {
                "accuracy": 0.8824867323730099,
                "n_samples": 1319
            },
            "tool": {
                "accuracy": 0.866565579984837,
                "program_accuracy": 0.868081880212282,
                "n_samples": 1319
            }
        }
    },
    "DeepSeekMath-Instruct": {
        "gsm8k-test": {
            "cot": {
                "accuracy": 0.8286580742987112,
                "n_samples": 1319
            },
            "tool": {
                "accuracy": 0.8369977255496588,
                "program_accuracy": 0.8332069749810462,
                "n_samples": 1319
            }
        },
        "math-test": {
            "cot": {
                "accuracy": 0.4682,
                "n_samples": 5000
            },
            "tool": {
                "accuracy": 0.575,
                "program_accuracy": 0.4664,
                "n_samples": 5000
            }
        },
        "cmath": {
            "cot": {
                "accuracy": 0.8460837887067395,
                "n_samples": 1098
            },
            "tool": {
                "accuracy": 0.843351548269581,
                "program_accuracy": 0.8214936247723132,
                "n_samples": 1098
            }
        },
        "mgsm-zh": {
            "cot": {
                "accuracy": 0.732,
                "n_samples": 250
            },
            "tool": {
                "accuracy": 0.72,
                "program_accuracy": 0.716,
                "n_samples": 250
            }
        }
    }
}