ZebraLogic / ZeroEval-main /result_dirs /zebra-grid.summary.json
yuchenlin's picture
Update ZeroEval-main/result_dirs/zebra-grid.summary.json
01d80b4 verified
[
{
"Model": "o3-mini-2025-01-31-high",
"Mode": "greedy",
"Puzzle Acc": "91.70",
"Cell Acc": "95.70",
"No answer": "0.30",
"Easy Puzzle Acc": "99.64",
"Hard Puzzle Acc": "88.61",
"Small Puzzle Acc": "99.69",
"Medium Puzzle Acc": "97.14",
"Large Puzzle Acc": "87.50",
"XL Puzzle Acc": "75.50",
"Total Puzzles": 1000,
"Reason Lens": "1983.34",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "o3-mini-2025-01-31-medium",
"Mode": "greedy",
"Puzzle Acc": "88.90",
"Cell Acc": "90.41",
"No answer": "0.10",
"Easy Puzzle Acc": "99.64",
"Hard Puzzle Acc": "84.72",
"Small Puzzle Acc": "99.69",
"Medium Puzzle Acc": "97.86",
"Large Puzzle Acc": "88.00",
"XL Puzzle Acc": "60.00",
"Total Puzzles": 1000,
"Reason Lens": "2067.98",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "o1-2024-12-17",
"Mode": "greedy",
"Puzzle Acc": "81.00",
"Cell Acc": "78.74",
"No answer": "0.20",
"Easy Puzzle Acc": "98.21",
"Hard Puzzle Acc": "74.31",
"Small Puzzle Acc": "97.19",
"Medium Puzzle Acc": "92.14",
"Large Puzzle Acc": "78.00",
"XL Puzzle Acc": "42.50",
"Total Puzzles": 1000,
"Reason Lens": "1197.51",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "deepseek-R1",
"Mode": "greedy",
"Puzzle Acc": "78.70",
"Cell Acc": "80.54",
"No answer": "0.00",
"Easy Puzzle Acc": "98.57",
"Hard Puzzle Acc": "70.97",
"Small Puzzle Acc": "98.44",
"Medium Puzzle Acc": "95.71",
"Large Puzzle Acc": "73.50",
"XL Puzzle Acc": "28.50",
"Total Puzzles": 1000,
"Reason Lens": "586.33",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "o3-mini-2025-01-31-low",
"Mode": "greedy",
"Puzzle Acc": "74.80",
"Cell Acc": "72.60",
"No answer": "1.60",
"Easy Puzzle Acc": "99.29",
"Hard Puzzle Acc": "65.28",
"Small Puzzle Acc": "99.38",
"Medium Puzzle Acc": "91.07",
"Large Puzzle Acc": "64.50",
"XL Puzzle Acc": "23.00",
"Total Puzzles": 1000,
"Reason Lens": "2080.78",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "o1-preview-2024-09-12",
"Mode": "greedy",
"Puzzle Acc": "71.40",
"Cell Acc": "75.14",
"No answer": "0.30",
"Easy Puzzle Acc": "98.57",
"Hard Puzzle Acc": "60.83",
"Small Puzzle Acc": "98.12",
"Medium Puzzle Acc": "88.21",
"Large Puzzle Acc": "59.50",
"XL Puzzle Acc": "17.00",
"Total Puzzles": 1000,
"Reason Lens": "1565.88",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "o1-preview-2024-09-12-v2",
"Mode": "greedy",
"Puzzle Acc": "70.40",
"Cell Acc": "74.18",
"No answer": "0.40",
"Easy Puzzle Acc": "98.21",
"Hard Puzzle Acc": "59.58",
"Small Puzzle Acc": "97.81",
"Medium Puzzle Acc": "88.57",
"Large Puzzle Acc": "55.50",
"XL Puzzle Acc": "16.00",
"Total Puzzles": 1000,
"Reason Lens": "1559.71",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "o1-mini-2024-09-12-v3",
"Mode": "greedy",
"Puzzle Acc": "59.70",
"Cell Acc": "70.32",
"No answer": "1.00",
"Easy Puzzle Acc": "86.07",
"Hard Puzzle Acc": "49.44",
"Small Puzzle Acc": "87.50",
"Medium Puzzle Acc": "76.79",
"Large Puzzle Acc": "39.00",
"XL Puzzle Acc": "12.00",
"Total Puzzles": 1000,
"Reason Lens": "1166.38",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "o1-mini-2024-09-12-v2",
"Mode": "greedy",
"Puzzle Acc": "56.80",
"Cell Acc": "69.87",
"No answer": "1.30",
"Easy Puzzle Acc": "82.86",
"Hard Puzzle Acc": "46.67",
"Small Puzzle Acc": "83.44",
"Medium Puzzle Acc": "76.43",
"Large Puzzle Acc": "36.00",
"XL Puzzle Acc": "7.50",
"Total Puzzles": 1000,
"Reason Lens": "1164.95",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "o1-mini-2024-09-12",
"Mode": "greedy",
"Puzzle Acc": "52.60",
"Cell Acc": "52.29",
"No answer": "0.80",
"Easy Puzzle Acc": "87.14",
"Hard Puzzle Acc": "39.17",
"Small Puzzle Acc": "87.81",
"Medium Puzzle Acc": "67.50",
"Large Puzzle Acc": "24.50",
"XL Puzzle Acc": "3.50",
"Total Puzzles": 1000,
"Reason Lens": "993.28",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "deepseek-v3",
"Mode": "greedy",
"Puzzle Acc": "42.10",
"Cell Acc": "42.04",
"No answer": "27.90",
"Easy Puzzle Acc": "90.00",
"Hard Puzzle Acc": "23.47",
"Small Puzzle Acc": "85.62",
"Medium Puzzle Acc": "44.64",
"Large Puzzle Acc": "10.00",
"XL Puzzle Acc": "1.00",
"Total Puzzles": 1000,
"Reason Lens": "2158.00",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "claude-3-5-sonnet-20241022",
"Mode": "greedy",
"Puzzle Acc": "36.20",
"Cell Acc": "54.27",
"No answer": "0.00",
"Easy Puzzle Acc": "91.07",
"Hard Puzzle Acc": "14.86",
"Small Puzzle Acc": "84.69",
"Medium Puzzle Acc": "28.93",
"Large Puzzle Acc": "4.00",
"XL Puzzle Acc": "1.00",
"Total Puzzles": 1000,
"Reason Lens": "861.18",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "claude-3-5-sonnet-20240620",
"Mode": "greedy",
"Puzzle Acc": "33.40",
"Cell Acc": "54.34",
"No answer": "0.00",
"Easy Puzzle Acc": "87.50",
"Hard Puzzle Acc": "12.36",
"Small Puzzle Acc": "83.44",
"Medium Puzzle Acc": "21.79",
"Large Puzzle Acc": "3.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1141.94",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Llama-3.1-405B-Inst-fp8@together",
"Mode": "greedy",
"Puzzle Acc": "32.60",
"Cell Acc": "45.80",
"No answer": "12.50",
"Easy Puzzle Acc": "87.14",
"Hard Puzzle Acc": "11.39",
"Small Puzzle Acc": "81.25",
"Medium Puzzle Acc": "22.50",
"Large Puzzle Acc": "1.50",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "314.66",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gpt-4o-2024-08-06",
"Mode": "greedy",
"Puzzle Acc": "31.70",
"Cell Acc": "50.34",
"No answer": "3.60",
"Easy Puzzle Acc": "84.64",
"Hard Puzzle Acc": "11.11",
"Small Puzzle Acc": "80.00",
"Medium Puzzle Acc": "19.64",
"Large Puzzle Acc": "2.50",
"XL Puzzle Acc": "0.50",
"Total Puzzles": 1000,
"Reason Lens": "1106.51",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gemini-1.5-pro-exp-0827",
"Mode": "greedy",
"Puzzle Acc": "30.50",
"Cell Acc": "50.84",
"No answer": "0.80",
"Easy Puzzle Acc": "79.64",
"Hard Puzzle Acc": "11.39",
"Small Puzzle Acc": "75.31",
"Medium Puzzle Acc": "20.71",
"Large Puzzle Acc": "3.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1594.47",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Llama-3.1-405B-Inst@sambanova",
"Mode": "greedy",
"Puzzle Acc": "30.10",
"Cell Acc": "39.06",
"No answer": "24.70",
"Easy Puzzle Acc": "84.64",
"Hard Puzzle Acc": "8.89",
"Small Puzzle Acc": "79.06",
"Medium Puzzle Acc": "16.43",
"Large Puzzle Acc": "0.50",
"XL Puzzle Acc": "0.50",
"Total Puzzles": 1000,
"Reason Lens": "2001.12",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "chatgpt-4o-latest-24-09-07",
"Mode": "greedy",
"Puzzle Acc": "29.90",
"Cell Acc": "48.83",
"No answer": "4.20",
"Easy Puzzle Acc": "81.43",
"Hard Puzzle Acc": "9.86",
"Small Puzzle Acc": "76.88",
"Medium Puzzle Acc": "17.86",
"Large Puzzle Acc": "1.50",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1539.99",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Mistral-Large-2",
"Mode": "greedy",
"Puzzle Acc": "29.00",
"Cell Acc": "47.64",
"No answer": "1.70",
"Easy Puzzle Acc": "80.36",
"Hard Puzzle Acc": "9.03",
"Small Puzzle Acc": "75.94",
"Medium Puzzle Acc": "15.00",
"Large Puzzle Acc": "2.50",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1592.39",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gpt-4-turbo-2024-04-09",
"Mode": "greedy",
"Puzzle Acc": "28.40",
"Cell Acc": "47.90",
"No answer": "0.10",
"Easy Puzzle Acc": "80.71",
"Hard Puzzle Acc": "8.06",
"Small Puzzle Acc": "75.31",
"Medium Puzzle Acc": "15.00",
"Large Puzzle Acc": "0.50",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1148.46",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gpt-4o-2024-05-13",
"Mode": "greedy",
"Puzzle Acc": "28.20",
"Cell Acc": "38.72",
"No answer": "19.30",
"Easy Puzzle Acc": "77.86",
"Hard Puzzle Acc": "8.89",
"Small Puzzle Acc": "73.75",
"Medium Puzzle Acc": "16.43",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1643.51",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "grok-2-1212",
"Mode": "greedy",
"Puzzle Acc": "27.70",
"Cell Acc": "48.16",
"No answer": "3.50",
"Easy Puzzle Acc": "76.43",
"Hard Puzzle Acc": "8.75",
"Small Puzzle Acc": "71.88",
"Medium Puzzle Acc": "13.93",
"Large Puzzle Acc": "4.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "2551.39",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gpt-4-0314",
"Mode": "greedy",
"Puzzle Acc": "27.10",
"Cell Acc": "47.43",
"No answer": "0.20",
"Easy Puzzle Acc": "77.14",
"Hard Puzzle Acc": "7.64",
"Small Puzzle Acc": "71.25",
"Medium Puzzle Acc": "13.57",
"Large Puzzle Acc": "2.50",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1203.17",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "claude-3-opus-20240229",
"Mode": "greedy",
"Puzzle Acc": "27.00",
"Cell Acc": "48.91",
"No answer": "0.00",
"Easy Puzzle Acc": "78.21",
"Hard Puzzle Acc": "7.08",
"Small Puzzle Acc": "73.44",
"Medium Puzzle Acc": "12.14",
"Large Puzzle Acc": "0.50",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "855.72",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Qwen2.5-72B-Instruct",
"Mode": "greedy",
"Puzzle Acc": "26.60",
"Cell Acc": "40.92",
"No answer": "11.90",
"Easy Puzzle Acc": "76.43",
"Hard Puzzle Acc": "7.22",
"Small Puzzle Acc": "72.50",
"Medium Puzzle Acc": "12.14",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1795.90",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Qwen2.5-32B-Instruct",
"Mode": "greedy",
"Puzzle Acc": "26.10",
"Cell Acc": "43.39",
"No answer": "6.30",
"Easy Puzzle Acc": "77.50",
"Hard Puzzle Acc": "6.11",
"Small Puzzle Acc": "72.19",
"Medium Puzzle Acc": "10.36",
"Large Puzzle Acc": "0.50",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1333.07",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gemini-1.5-pro-exp-0801",
"Mode": "greedy",
"Puzzle Acc": "25.20",
"Cell Acc": "48.50",
"No answer": "0.00",
"Easy Puzzle Acc": "72.50",
"Hard Puzzle Acc": "6.81",
"Small Puzzle Acc": "66.56",
"Medium Puzzle Acc": "13.93",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1389.75",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Llama-3.1-405B-Inst@hyperbolic",
"Mode": "greedy",
"Puzzle Acc": "25.00",
"Cell Acc": "46.62",
"No answer": "6.25",
"Easy Puzzle Acc": "66.67",
"Hard Puzzle Acc": "15.38",
"Small Puzzle Acc": "50.00",
"Medium Puzzle Acc": "33.33",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 16,
"Reason Lens": "1517.13",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gemini-1.5-flash-exp-0827",
"Mode": "greedy",
"Puzzle Acc": "25.00",
"Cell Acc": "43.56",
"No answer": "8.50",
"Easy Puzzle Acc": "70.71",
"Hard Puzzle Acc": "7.22",
"Small Puzzle Acc": "65.00",
"Medium Puzzle Acc": "13.57",
"Large Puzzle Acc": "2.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1705.11",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Meta-Llama-3.1-70B-Instruct",
"Mode": "greedy",
"Puzzle Acc": "24.90",
"Cell Acc": "27.98",
"No answer": "43.00",
"Easy Puzzle Acc": "73.57",
"Hard Puzzle Acc": "5.97",
"Small Puzzle Acc": "67.81",
"Medium Puzzle Acc": "10.36",
"Large Puzzle Acc": "1.50",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1483.68",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "deepseek-v2-chat-0628",
"Mode": "greedy",
"Puzzle Acc": "22.70",
"Cell Acc": "42.46",
"No answer": "5.20",
"Easy Puzzle Acc": "68.57",
"Hard Puzzle Acc": "4.86",
"Small Puzzle Acc": "63.44",
"Medium Puzzle Acc": "8.57",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1260.23",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "deepseek-v2.5-0908",
"Mode": "greedy",
"Puzzle Acc": "22.10",
"Cell Acc": "38.01",
"No answer": "12.70",
"Easy Puzzle Acc": "68.21",
"Hard Puzzle Acc": "4.17",
"Small Puzzle Acc": "62.19",
"Medium Puzzle Acc": "7.86",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1294.46",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Qwen2-72B-Instruct",
"Mode": "greedy",
"Puzzle Acc": "21.40",
"Cell Acc": "38.32",
"No answer": "10.20",
"Easy Puzzle Acc": "63.93",
"Hard Puzzle Acc": "4.86",
"Small Puzzle Acc": "60.94",
"Medium Puzzle Acc": "6.79",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1813.82",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "deepseek-v2-coder-0614",
"Mode": "greedy",
"Puzzle Acc": "21.10",
"Cell Acc": "41.58",
"No answer": "4.90",
"Easy Puzzle Acc": "64.64",
"Hard Puzzle Acc": "4.17",
"Small Puzzle Acc": "59.69",
"Medium Puzzle Acc": "7.14",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1324.55",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "deepseek-v2-coder-0724",
"Mode": "greedy",
"Puzzle Acc": "20.50",
"Cell Acc": "42.35",
"No answer": "3.40",
"Easy Puzzle Acc": "61.79",
"Hard Puzzle Acc": "4.44",
"Small Puzzle Acc": "57.50",
"Medium Puzzle Acc": "7.14",
"Large Puzzle Acc": "0.50",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1230.63",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gpt-4o-mini-2024-07-18",
"Mode": "greedy",
"Puzzle Acc": "20.10",
"Cell Acc": "41.26",
"No answer": "0.10",
"Easy Puzzle Acc": "62.50",
"Hard Puzzle Acc": "3.61",
"Small Puzzle Acc": "58.75",
"Medium Puzzle Acc": "4.64",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "943.52",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gemini-1.5-flash",
"Mode": "greedy",
"Puzzle Acc": "19.40",
"Cell Acc": "31.77",
"No answer": "22.70",
"Easy Puzzle Acc": "59.29",
"Hard Puzzle Acc": "3.89",
"Small Puzzle Acc": "55.00",
"Medium Puzzle Acc": "6.43",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1538.18",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gemini-1.5-pro",
"Mode": "greedy",
"Puzzle Acc": "19.40",
"Cell Acc": "44.59",
"No answer": "0.80",
"Easy Puzzle Acc": "55.71",
"Hard Puzzle Acc": "5.28",
"Small Puzzle Acc": "52.19",
"Medium Puzzle Acc": "9.64",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1336.17",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "yi-large-preview",
"Mode": "greedy",
"Puzzle Acc": "18.90",
"Cell Acc": "42.61",
"No answer": "1.40",
"Easy Puzzle Acc": "58.93",
"Hard Puzzle Acc": "3.33",
"Small Puzzle Acc": "53.75",
"Medium Puzzle Acc": "6.07",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "833.36",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "yi-large",
"Mode": "greedy",
"Puzzle Acc": "18.80",
"Cell Acc": "39.83",
"No answer": "1.80",
"Easy Puzzle Acc": "58.21",
"Hard Puzzle Acc": "3.47",
"Small Puzzle Acc": "54.37",
"Medium Puzzle Acc": "5.00",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "757.01",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "claude-3-5-haiku-20241022",
"Mode": "greedy",
"Puzzle Acc": "18.70",
"Cell Acc": "43.22",
"No answer": "0.10",
"Easy Puzzle Acc": "57.86",
"Hard Puzzle Acc": "3.47",
"Small Puzzle Acc": "53.12",
"Medium Puzzle Acc": "6.07",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "660.91",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "claude-3-sonnet-20240229",
"Mode": "greedy",
"Puzzle Acc": "18.70",
"Cell Acc": "43.66",
"No answer": "0.00",
"Easy Puzzle Acc": "58.93",
"Hard Puzzle Acc": "3.06",
"Small Puzzle Acc": "54.06",
"Medium Puzzle Acc": "4.29",
"Large Puzzle Acc": "1.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1095.37",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Meta-Llama-3-70B-Instruct",
"Mode": "greedy",
"Puzzle Acc": "16.80",
"Cell Acc": "42.31",
"No answer": "0.20",
"Easy Puzzle Acc": "52.86",
"Hard Puzzle Acc": "2.78",
"Small Puzzle Acc": "48.44",
"Medium Puzzle Acc": "4.64",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "809.95",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Athene-70B",
"Mode": "greedy",
"Puzzle Acc": "16.70",
"Cell Acc": "32.98",
"No answer": "21.10",
"Easy Puzzle Acc": "52.50",
"Hard Puzzle Acc": "2.78",
"Small Puzzle Acc": "48.75",
"Medium Puzzle Acc": "3.93",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "391.19",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gemma-2-27b-it",
"Mode": "greedy",
"Puzzle Acc": "16.30",
"Cell Acc": "41.18",
"No answer": "1.10",
"Easy Puzzle Acc": "50.71",
"Hard Puzzle Acc": "2.92",
"Small Puzzle Acc": "46.56",
"Medium Puzzle Acc": "5.00",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1014.56",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "claude-3-haiku-20240307",
"Mode": "greedy",
"Puzzle Acc": "14.30",
"Cell Acc": "37.87",
"No answer": "0.10",
"Easy Puzzle Acc": "47.86",
"Hard Puzzle Acc": "1.25",
"Small Puzzle Acc": "43.75",
"Medium Puzzle Acc": "1.07",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1015.06",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "command-r-plus",
"Mode": "greedy",
"Puzzle Acc": "13.90",
"Cell Acc": "39.01",
"No answer": "0.20",
"Easy Puzzle Acc": "44.64",
"Hard Puzzle Acc": "1.94",
"Small Puzzle Acc": "40.94",
"Medium Puzzle Acc": "2.86",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "810.53",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "reka-core-20240501",
"Mode": "greedy",
"Puzzle Acc": "13.00",
"Cell Acc": "33.88",
"No answer": "4.00",
"Easy Puzzle Acc": "43.21",
"Hard Puzzle Acc": "1.25",
"Small Puzzle Acc": "39.38",
"Medium Puzzle Acc": "1.43",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1078.29",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gemma-2-9b-it",
"Mode": "greedy",
"Puzzle Acc": "12.80",
"Cell Acc": "36.79",
"No answer": "0.00",
"Easy Puzzle Acc": "41.79",
"Hard Puzzle Acc": "1.53",
"Small Puzzle Acc": "37.81",
"Medium Puzzle Acc": "2.50",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "849.84",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Meta-Llama-3.1-8B-Instruct",
"Mode": "greedy",
"Puzzle Acc": "12.80",
"Cell Acc": "13.68",
"No answer": "61.50",
"Easy Puzzle Acc": "43.57",
"Hard Puzzle Acc": "0.83",
"Small Puzzle Acc": "39.38",
"Medium Puzzle Acc": "0.71",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1043.90",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Qwen2.5-7B-Instruct",
"Mode": "greedy",
"Puzzle Acc": "12.00",
"Cell Acc": "30.67",
"No answer": "9.50",
"Easy Puzzle Acc": "38.93",
"Hard Puzzle Acc": "1.53",
"Small Puzzle Acc": "36.25",
"Medium Puzzle Acc": "1.43",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "850.93",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Meta-Llama-3-8B-Instruct",
"Mode": "greedy",
"Puzzle Acc": "11.90",
"Cell Acc": "23.70",
"No answer": "29.20",
"Easy Puzzle Acc": "40.71",
"Hard Puzzle Acc": "0.69",
"Small Puzzle Acc": "36.88",
"Medium Puzzle Acc": "0.36",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1216.40",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Mistral-Nemo-Instruct-2407",
"Mode": "greedy",
"Puzzle Acc": "11.80",
"Cell Acc": "34.93",
"No answer": "1.60",
"Easy Puzzle Acc": "38.93",
"Hard Puzzle Acc": "1.25",
"Small Puzzle Acc": "35.31",
"Medium Puzzle Acc": "1.79",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "925.88",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Phi-3-mini-4k-instruct",
"Mode": "greedy",
"Puzzle Acc": "11.60",
"Cell Acc": "13.50",
"No answer": "59.00",
"Easy Puzzle Acc": "38.21",
"Hard Puzzle Acc": "1.25",
"Small Puzzle Acc": "35.94",
"Medium Puzzle Acc": "0.36",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "790.29",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Yi-1.5-34B-Chat",
"Mode": "greedy",
"Puzzle Acc": "11.50",
"Cell Acc": "32.73",
"No answer": "4.40",
"Easy Puzzle Acc": "37.50",
"Hard Puzzle Acc": "1.39",
"Small Puzzle Acc": "35.00",
"Medium Puzzle Acc": "1.07",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "869.65",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gpt-3.5-turbo-0125",
"Mode": "greedy",
"Puzzle Acc": "10.10",
"Cell Acc": "33.06",
"No answer": "0.10",
"Easy Puzzle Acc": "33.57",
"Hard Puzzle Acc": "0.97",
"Small Puzzle Acc": "30.31",
"Medium Puzzle Acc": "1.07",
"Large Puzzle Acc": "0.50",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "820.66",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "command-r",
"Mode": "greedy",
"Puzzle Acc": "9.90",
"Cell Acc": "32.66",
"No answer": "1.50",
"Easy Puzzle Acc": "32.14",
"Hard Puzzle Acc": "1.25",
"Small Puzzle Acc": "30.31",
"Medium Puzzle Acc": "0.71",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1005.17",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "reka-flash-20240226",
"Mode": "greedy",
"Puzzle Acc": "9.30",
"Cell Acc": "25.67",
"No answer": "18.70",
"Easy Puzzle Acc": "30.71",
"Hard Puzzle Acc": "0.97",
"Small Puzzle Acc": "28.44",
"Medium Puzzle Acc": "0.71",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1074.80",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "mathstral-7B-v0.1",
"Mode": "greedy",
"Puzzle Acc": "9.00",
"Cell Acc": "20.42",
"No answer": "36.00",
"Easy Puzzle Acc": "30.00",
"Hard Puzzle Acc": "0.83",
"Small Puzzle Acc": "27.19",
"Medium Puzzle Acc": "1.07",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1148.16",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Mixtral-8x7B-Instruct-v0.1",
"Mode": "greedy",
"Puzzle Acc": "8.70",
"Cell Acc": "26.47",
"No answer": "20.30",
"Easy Puzzle Acc": "28.93",
"Hard Puzzle Acc": "0.83",
"Small Puzzle Acc": "26.25",
"Medium Puzzle Acc": "1.07",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1177.21",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Qwen2-7B-Instruct",
"Mode": "greedy",
"Puzzle Acc": "8.40",
"Cell Acc": "22.06",
"No answer": "24.40",
"Easy Puzzle Acc": "29.29",
"Hard Puzzle Acc": "0.28",
"Small Puzzle Acc": "26.25",
"Medium Puzzle Acc": "0.00",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1473.23",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Llama-3.2-3B-Instruct@together",
"Mode": "greedy",
"Puzzle Acc": "7.40",
"Cell Acc": "13.14",
"No answer": "54.50",
"Easy Puzzle Acc": "25.71",
"Hard Puzzle Acc": "0.28",
"Small Puzzle Acc": "23.12",
"Medium Puzzle Acc": "0.00",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "963.47",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Phi-3.5-mini-instruct",
"Mode": "greedy",
"Puzzle Acc": "6.40",
"Cell Acc": "5.98",
"No answer": "80.60",
"Easy Puzzle Acc": "21.79",
"Hard Puzzle Acc": "0.42",
"Small Puzzle Acc": "19.38",
"Medium Puzzle Acc": "0.71",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "718.43",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Qwen2.5-3B-Instruct",
"Mode": "greedy",
"Puzzle Acc": "4.80",
"Cell Acc": "11.44",
"No answer": "56.70",
"Easy Puzzle Acc": "17.14",
"Hard Puzzle Acc": "0.00",
"Small Puzzle Acc": "15.00",
"Medium Puzzle Acc": "0.00",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "906.58",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "gemma-2-2b-it",
"Mode": "greedy",
"Puzzle Acc": "4.20",
"Cell Acc": "9.97",
"No answer": "57.20",
"Easy Puzzle Acc": "14.29",
"Hard Puzzle Acc": "0.28",
"Small Puzzle Acc": "13.12",
"Medium Puzzle Acc": "0.00",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1032.89",
"N_Mode": "single",
"N_Size": 1
},
{
"Model": "Yi-1.5-9B-Chat",
"Mode": "greedy",
"Puzzle Acc": "2.30",
"Cell Acc": "7.53",
"No answer": "11.30",
"Easy Puzzle Acc": "8.21",
"Hard Puzzle Acc": "0.00",
"Small Puzzle Acc": "7.19",
"Medium Puzzle Acc": "0.00",
"Large Puzzle Acc": "0.00",
"XL Puzzle Acc": "0.00",
"Total Puzzles": 1000,
"Reason Lens": "1592.60",
"N_Mode": "single",
"N_Size": 1
}
]