Hugging Face's logo

Spaces:
Enderchef
/
SuperBench-Eval
Running on Zero

App Files Community
Enderchef commited on
Commit
02583ad
·
verified ·
1 Parent(s): 2423db5

Update eval.jsonl

Browse files
Files changed (1) hide show
  1. eval.jsonl +6 -6
eval.jsonl CHANGED
@@ -1,6 +1,6 @@
1
- {"model_id": "Gemini 2.5 Pro", "benchmark": "MMLU", "subject": "ALL", "accuracy": 88.00, "sample_count": 1000, "timestamp": "2025-06-25T14:17:00.000000"}
2
- {"model_id": "ChatGPT 4.5", "benchmark": "MMLU", "subject": "ALL", "accuracy": 86.50, "sample_count": 1000, "timestamp": "2025-06-25T14:17:01.000000"}
3
- {"model_id": "Llama 4 Scout", "benchmark": "MMLU", "subject": "ALL", "accuracy": 85.00, "sample_count": 1000, "timestamp": "2025-06-25T14:17:02.000000"}
4
- {"model_id": "Qwen3 235B A22B", "benchmark": "MMLU", "subject": "ALL", "accuracy": 87.20, "sample_count": 1000, "timestamp": "2025-06-25T14:17:03.000000"}
5
- {"model_id": "Mistral-Small-3.2-24B-Instruct-2506", "benchmark": "MMLU", "subject": "ALL", "accuracy": 84.80, "sample_count": 1000, "timestamp": "2025-06-25T14:17:04.000000"}
6
- {"model_id": "Claude 4 Opus", "benchmark": "MMLU", "subject": "ALL", "accuracy": 89.10, "sample_count": 1000, "timestamp": "2025-06-25T14:17:05.000000"}
 
1
+ {"model_id": "Gemini 2.5 Pro(Not on hub)", "benchmark": "MMLU", "subject": "ALL", "accuracy": 88.00, "sample_count": 1000, "timestamp": "2025-06-25T14:17:00.000000"}
2
+ {"model_id": "ChatGPT 4.5(Not on hub)", "benchmark": "MMLU", "subject": "ALL", "accuracy": 86.50, "sample_count": 1000, "timestamp": "2025-06-25T14:17:01.000000"}
3
+ {"model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "benchmark": "MMLU", "subject": "ALL", "accuracy": 85.00, "sample_count": 1000, "timestamp": "2025-06-25T14:17:02.000000"}
4
+ {"model_id": "Qwen/Qwen3-235B-A22B", "benchmark": "MMLU", "subject": "ALL", "accuracy": 87.20, "sample_count": 1000, "timestamp": "2025-06-25T14:17:03.000000"}
5
+ {"model_id": "Mistralai/Mistral-Small-3.2-24B-Instruct-2506", "benchmark": "MMLU", "subject": "ALL", "accuracy": 84.80, "sample_count": 1000, "timestamp": "2025-06-25T14:17:04.000000"}
6
+ {"model_id": "Claude 4 Opus(Not on hub)", "benchmark": "MMLU", "subject": "ALL", "accuracy": 89.10, "sample_count": 1000, "timestamp": "2025-06-25T14:17:05.000000"}