784 lines
19 KiB
JSON
784 lines
19 KiB
JSON
[
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4"
|
|
],
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:20:31.673Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4\n"
|
|
],
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:20:33.287Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4"
|
|
],
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:20:34.328Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4"
|
|
],
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:21:49.790Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4\n"
|
|
],
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:21:51.896Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4"
|
|
],
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:21:52.849Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4"
|
|
],
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:24:35.975Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4\n"
|
|
],
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:24:37.455Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4"
|
|
],
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:24:38.366Z"
|
|
},
|
|
{
|
|
"test": "json_structure",
|
|
"prompt": "return a JSON object with two fields: \"name\" as \"test\" and \"value\" as 42. Return only the JSON, no other text.",
|
|
"result": [
|
|
"{\"name\": \"test\", \"value\": 42}"
|
|
],
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:24:39.480Z"
|
|
},
|
|
{
|
|
"test": "json_structure",
|
|
"prompt": "return a JSON object with two fields: \"name\" as \"test\" and \"value\" as 42. Return only the JSON, no other text.",
|
|
"result": [
|
|
"{\"name\": \"test\", \"value\": 42}"
|
|
],
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:24:42.228Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4"
|
|
],
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:25:06.304Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4\n"
|
|
],
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:25:07.392Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4"
|
|
],
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:25:08.429Z"
|
|
},
|
|
{
|
|
"test": "json_structure",
|
|
"prompt": "return a JSON object with two fields: \"name\" as \"test\" and \"value\" as 42. Return only the JSON, no other text.",
|
|
"result": [
|
|
"```json\n{\"name\":\"test\",\"value\":42}\n```"
|
|
],
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:25:09.627Z"
|
|
},
|
|
{
|
|
"test": "json_structure",
|
|
"prompt": "return a JSON object with two fields: \"name\" as \"test\" and \"value\" as 42. Return only the JSON, no other text.",
|
|
"result": [
|
|
"```json\n{\n \"name\": \"test\",\n \"value\": 42\n}\n```\n"
|
|
],
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:25:10.720Z"
|
|
},
|
|
{
|
|
"test": "json_structure",
|
|
"prompt": "return a JSON object with two fields: \"name\" as \"test\" and \"value\" as 42. Return only the JSON, no other text.",
|
|
"result": [
|
|
"{\"name\": \"test\", \"value\": 42}"
|
|
],
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:25:12.099Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4"
|
|
],
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:26:30.128Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4\n"
|
|
],
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:26:31.316Z"
|
|
},
|
|
{
|
|
"test": "basic_arithmetic",
|
|
"prompt": "return the result of 2+2, dont comment",
|
|
"result": [
|
|
"4"
|
|
],
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:26:32.279Z"
|
|
},
|
|
{
|
|
"test": "json_structure",
|
|
"prompt": "return a JSON object with two fields: \"name\" as \"test\" and \"value\" as 42. Return only the JSON, no other text.",
|
|
"result": [
|
|
"{\"name\":\"test\",\"value\":42}"
|
|
],
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:26:33.459Z"
|
|
},
|
|
{
|
|
"test": "json_structure",
|
|
"prompt": "return a JSON object with two fields: \"name\" as \"test\" and \"value\" as 42. Return only the JSON, no other text.",
|
|
"result": [
|
|
"{\n \"name\": \"test\",\n \"value\": 42\n}"
|
|
],
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:26:35.012Z"
|
|
},
|
|
{
|
|
"test": "json_structure",
|
|
"prompt": "return a JSON object with two fields: \"name\" as \"test\" and \"value\" as 42. Return only the JSON, no other text.",
|
|
"result": [
|
|
"{\"name\": \"test\", \"value\": 42}"
|
|
],
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:26:36.239Z"
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8"
|
|
],
|
|
"expected": "8",
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:46:03.882Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8\n"
|
|
],
|
|
"expected": "8",
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:46:05.343Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8"
|
|
],
|
|
"expected": "8",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:46:06.365Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 4 and 6. Return only the number, no explanation.",
|
|
"result": [
|
|
"24"
|
|
],
|
|
"expected": "24",
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:46:07.564Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 4 and 6. Return only the number, no explanation.",
|
|
"result": [
|
|
"24\n"
|
|
],
|
|
"expected": "24",
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:46:09.013Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 4 and 6. Return only the number, no explanation.",
|
|
"result": [
|
|
"24"
|
|
],
|
|
"expected": "24",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:46:09.968Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5"
|
|
],
|
|
"expected": "5",
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:46:10.981Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5\n"
|
|
],
|
|
"expected": "5",
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:46:12.829Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5"
|
|
],
|
|
"expected": "5",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:46:13.957Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8"
|
|
],
|
|
"expected": "8",
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:53:47.732Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8\n"
|
|
],
|
|
"expected": "8",
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:53:50.075Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8"
|
|
],
|
|
"expected": "8",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:53:50.977Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 4 and 6. Return only the number, no explanation.",
|
|
"result": [
|
|
"24"
|
|
],
|
|
"expected": "24",
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:53:52.835Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 4 and 6. Return only the number, no explanation.",
|
|
"result": [
|
|
"24\n"
|
|
],
|
|
"expected": "24",
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:53:54.875Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 4 and 6. Return only the number, no explanation.",
|
|
"result": [
|
|
"24"
|
|
],
|
|
"expected": "24",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:53:55.866Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5"
|
|
],
|
|
"expected": "5",
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:53:56.950Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5"
|
|
],
|
|
"expected": "5",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:53:59.317Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8"
|
|
],
|
|
"expected": "8",
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:56:01.223Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8\n"
|
|
],
|
|
"expected": "8",
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:56:02.717Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8"
|
|
],
|
|
"expected": "8",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:56:03.867Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 4 and 6. Return only the number, no explanation.",
|
|
"result": [
|
|
"24"
|
|
],
|
|
"expected": "24",
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:56:04.864Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 4 and 6. Return only the number, no explanation.",
|
|
"result": [
|
|
"24\n"
|
|
],
|
|
"expected": "24",
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:56:05.973Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 4 and 6. Return only the number, no explanation.",
|
|
"result": [
|
|
"24"
|
|
],
|
|
"expected": "24",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:56:07.075Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5"
|
|
],
|
|
"expected": "5",
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:56:08.103Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5\n"
|
|
],
|
|
"expected": "5",
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:56:09.298Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5"
|
|
],
|
|
"expected": "5",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:56:10.178Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8"
|
|
],
|
|
"expected": "8",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:56:32.641Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 4 and 6. Return only the number, no explanation.",
|
|
"result": [
|
|
"24"
|
|
],
|
|
"expected": "24",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:56:35.038Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5"
|
|
],
|
|
"expected": "5",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:56:37.567Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8"
|
|
],
|
|
"expected": "8",
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:59:06.742Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8\n"
|
|
],
|
|
"expected": "8",
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:59:08.889Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8"
|
|
],
|
|
"expected": "8",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:59:09.871Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 8 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"24"
|
|
],
|
|
"expected": "24",
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:59:13.627Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 8 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"24\n"
|
|
],
|
|
"expected": "24",
|
|
"model": "google/gemini-2.0-flash-exp:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:59:15.963Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 8 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"24"
|
|
],
|
|
"expected": "24",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:59:17.124Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5"
|
|
],
|
|
"expected": "5",
|
|
"model": "deepseek/deepseek-chat:free",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:59:18.527Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5"
|
|
],
|
|
"expected": "5",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:59:20.298Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8"
|
|
],
|
|
"expected": "8",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T10:59:58.244Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 8 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"24"
|
|
],
|
|
"expected": "24",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T11:00:00.620Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5"
|
|
],
|
|
"expected": "5",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T11:00:03.143Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8"
|
|
],
|
|
"expected": "8",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T11:00:10.210Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 8 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"24"
|
|
],
|
|
"expected": "24",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T11:00:12.798Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5"
|
|
],
|
|
"expected": "5",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T11:00:15.604Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "addition",
|
|
"prompt": "add 5 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"8"
|
|
],
|
|
"expected": "8",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T11:00:35.256Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "multiplication",
|
|
"prompt": "multiply 8 and 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"24"
|
|
],
|
|
"expected": "24",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T11:00:37.681Z",
|
|
"passed": true
|
|
},
|
|
{
|
|
"test": "division",
|
|
"prompt": "divide 15 by 3. Return only the number, no explanation.",
|
|
"result": [
|
|
"5"
|
|
],
|
|
"expected": "5",
|
|
"model": "gpt-4",
|
|
"router": "openrouter",
|
|
"timestamp": "2025-04-01T11:00:40.556Z",
|
|
"passed": true
|
|
}
|
|
] |