|
2015 | 2015 | } |
2016 | 2016 | } |
2017 | 2017 | }, |
| 2018 | + "microsoft/Phi-3-small-128k-instruct": { |
| 2019 | + "eval_date": "2024-05-23 02:31:23.338528", |
| 2020 | + "train_size": "128k", |
| 2021 | + "scores": { |
| 2022 | + "all": { |
| 2023 | + "0.0": { "pass@1": 0.792 }, |
| 2024 | + "0.1": { "pass@1": 0.662 }, |
| 2025 | + "0.2": { "pass@1": 0.612 }, |
| 2026 | + "0.3": { "pass@1": 0.564 }, |
| 2027 | + "0.4": { "pass@1": 0.526 }, |
| 2028 | + "0.5": { "pass@1": 0.49 }, |
| 2029 | + "0.6": { "pass@1": 0.466 }, |
| 2030 | + "0.7": { "pass@1": 0.444 }, |
| 2031 | + "0.8": { "pass@1": 0.396 }, |
| 2032 | + "0.9": { "pass@1": 0.322 }, |
| 2033 | + "1.0": { "pass@1": 0.242 } |
| 2034 | + }, |
| 2035 | + "python": { |
| 2036 | + "0.0": { "pass@1": 0.74 }, |
| 2037 | + "0.1": { "pass@1": 0.57 }, |
| 2038 | + "0.2": { "pass@1": 0.52 }, |
| 2039 | + "0.3": { "pass@1": 0.46 }, |
| 2040 | + "0.4": { "pass@1": 0.41 }, |
| 2041 | + "0.5": { "pass@1": 0.36 }, |
| 2042 | + "0.6": { "pass@1": 0.34 }, |
| 2043 | + "0.7": { "pass@1": 0.29 }, |
| 2044 | + "0.8": { "pass@1": 0.25 }, |
| 2045 | + "0.9": { "pass@1": 0.23 }, |
| 2046 | + "1.0": { "pass@1": 0.21 } |
| 2047 | + }, |
| 2048 | + "cpp": { |
| 2049 | + "0.0": { "pass@1": 0.83 }, |
| 2050 | + "0.1": { "pass@1": 0.68 }, |
| 2051 | + "0.2": { "pass@1": 0.62 }, |
| 2052 | + "0.3": { "pass@1": 0.57 }, |
| 2053 | + "0.4": { "pass@1": 0.55 }, |
| 2054 | + "0.5": { "pass@1": 0.53 }, |
| 2055 | + "0.6": { "pass@1": 0.52 }, |
| 2056 | + "0.7": { "pass@1": 0.5 }, |
| 2057 | + "0.8": { "pass@1": 0.48 }, |
| 2058 | + "0.9": { "pass@1": 0.4 }, |
| 2059 | + "1.0": { "pass@1": 0.35 } |
| 2060 | + }, |
| 2061 | + "java": { |
| 2062 | + "0.0": { "pass@1": 0.83 }, |
| 2063 | + "0.1": { "pass@1": 0.74 }, |
| 2064 | + "0.2": { "pass@1": 0.69 }, |
| 2065 | + "0.3": { "pass@1": 0.67 }, |
| 2066 | + "0.4": { "pass@1": 0.6 }, |
| 2067 | + "0.5": { "pass@1": 0.58 }, |
| 2068 | + "0.6": { "pass@1": 0.55 }, |
| 2069 | + "0.7": { "pass@1": 0.53 }, |
| 2070 | + "0.8": { "pass@1": 0.46 }, |
| 2071 | + "0.9": { "pass@1": 0.39 }, |
| 2072 | + "1.0": { "pass@1": 0.3 } |
| 2073 | + }, |
| 2074 | + "typescript": { |
| 2075 | + "0.0": { "pass@1": 0.9 }, |
| 2076 | + "0.1": { "pass@1": 0.81 }, |
| 2077 | + "0.2": { "pass@1": 0.78 }, |
| 2078 | + "0.3": { "pass@1": 0.7 }, |
| 2079 | + "0.4": { "pass@1": 0.68 }, |
| 2080 | + "0.5": { "pass@1": 0.62 }, |
| 2081 | + "0.6": { "pass@1": 0.58 }, |
| 2082 | + "0.7": { "pass@1": 0.56 }, |
| 2083 | + "0.8": { "pass@1": 0.49 }, |
| 2084 | + "0.9": { "pass@1": 0.34 }, |
| 2085 | + "1.0": { "pass@1": 0.14 } |
| 2086 | + }, |
| 2087 | + "rust": { |
| 2088 | + "0.0": { "pass@1": 0.66 }, |
| 2089 | + "0.1": { "pass@1": 0.51 }, |
| 2090 | + "0.2": { "pass@1": 0.45 }, |
| 2091 | + "0.3": { "pass@1": 0.42 }, |
| 2092 | + "0.4": { "pass@1": 0.39 }, |
| 2093 | + "0.5": { "pass@1": 0.36 }, |
| 2094 | + "0.6": { "pass@1": 0.34 }, |
| 2095 | + "0.7": { "pass@1": 0.34 }, |
| 2096 | + "0.8": { "pass@1": 0.3 }, |
| 2097 | + "0.9": { "pass@1": 0.25 }, |
| 2098 | + "1.0": { "pass@1": 0.21 } |
| 2099 | + } |
| 2100 | + } |
| 2101 | + }, |
2018 | 2102 | "gemini-1.5-flash-latest": { |
2019 | 2103 | "eval_date": "2024-05-19 04:32:12.200298", |
2020 | 2104 | "train_size": "1000k", |
|
0 commit comments