Update README.md
Browse files
README.md
CHANGED
|
@@ -149,6 +149,8 @@ We evaluated the models using 100 examples from the dev split.
|
|
| 149 |
|
| 150 |
### Japanese MT Bench
|
| 151 |
|
|
|
|
|
|
|
| 152 |
| Model name | average | coding | extraction | humanities | math | reasoning | roleplay | stem | writing |
|
| 153 |
| :--- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 154 |
| [llm-jp-3-1.8b-instruct](https://huggingface.co/llm-jp/llm-jp-3-1.8b-instruct) | 4.93 | 1.50 | 4.70 | 7.80 | 1.55 | 2.60 | 7.80 | 6.10 | 7.40 |
|
|
|
|
| 149 |
|
| 150 |
### Japanese MT Bench
|
| 151 |
|
| 152 |
+
We evaluated the models using `gpt-4-0613`. Please see the [codes](https://github.com/llm-jp/llm-leaderboard/tree/main) for details.
|
| 153 |
+
|
| 154 |
| Model name | average | coding | extraction | humanities | math | reasoning | roleplay | stem | writing |
|
| 155 |
| :--- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 156 |
| [llm-jp-3-1.8b-instruct](https://huggingface.co/llm-jp/llm-jp-3-1.8b-instruct) | 4.93 | 1.50 | 4.70 | 7.80 | 1.55 | 2.60 | 7.80 | 6.10 | 7.40 |
|