Adding Evaluation Results
#13
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -92,4 +92,17 @@ Results on common sense reasoning benchmarks
|
|
| 92 |
| Open Assistant Pythia 12B | 67.9 | 78.0 | 68.1 | 65.0 | 64.2 | 40.4 | 43.2 | 61.0 |
|
| 93 |
| Mosaic mpt-7b | 74.8 | **79.3** | **76.3** | 68.6 | **70.0** | 42.2 | 42.6 | 64.8 |
|
| 94 |
| text-davinci-003 | 88.1 | 83.8 | 83.4 | 75.8 | 83.9 | 63.9 | 51.0 | 75.7 |
|
| 95 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
| Open Assistant Pythia 12B | 67.9 | 78.0 | 68.1 | 65.0 | 64.2 | 40.4 | 43.2 | 61.0 |
|
| 93 |
| Mosaic mpt-7b | 74.8 | **79.3** | **76.3** | 68.6 | **70.0** | 42.2 | 42.6 | 64.8 |
|
| 94 |
| text-davinci-003 | 88.1 | 83.8 | 83.4 | 75.8 | 83.9 | 63.9 | 51.0 | 75.7 |
|
| 95 |
+
```
|
| 96 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 97 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nomic-ai__gpt4all-j)
|
| 98 |
+
|
| 99 |
+
| Metric | Value |
|
| 100 |
+
|-----------------------|---------------------------|
|
| 101 |
+
| Avg. | 37.41 |
|
| 102 |
+
| ARC (25-shot) | 41.98 |
|
| 103 |
+
| HellaSwag (10-shot) | 64.06 |
|
| 104 |
+
| MMLU (5-shot) | 28.2 |
|
| 105 |
+
| TruthfulQA (0-shot) | 42.78 |
|
| 106 |
+
| Winogrande (5-shot) | 64.72 |
|
| 107 |
+
| GSM8K (5-shot) | 7.2 |
|
| 108 |
+
| DROP (3-shot) | 12.94 |
|