Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,34 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
+
Is an test train, full train on its way.. Looks promising?
|
| 5 |
+
|
| 6 |
+
**First Turn Scores**
|
| 7 |
+
|
| 8 |
+
| model | turn | score |
|
| 9 |
+
|----------------|------|---------|
|
| 10 |
+
| gpt-4 | 1 | 8.95625 |
|
| 11 |
+
| claude-v1 | 1 | 8.15000 |
|
| 12 |
+
| gpt-3.5-turbo | 1 | 8.07500 |
|
| 13 |
+
| LexGPT-V2 | 1 | 7.55625 |
|
| 14 |
+
| vicuna-13b-v1.3| 1 | 6.81250 |
|
| 15 |
+
|
| 16 |
+
**Second Turn Scores**
|
| 17 |
+
|
| 18 |
+
| model | turn | score |
|
| 19 |
+
|----------------|------|--------|
|
| 20 |
+
| gpt-4 | 2 | 9.0250 |
|
| 21 |
+
| gpt-3.5-turbo | 2 | 7.8125 |
|
| 22 |
+
| claude-v1 | 2 | 7.6500 |
|
| 23 |
+
| LexGPT-V2 | 2 | 6.8375 |
|
| 24 |
+
| vicuna-13b-v1.3| 2 | 5.9625 |
|
| 25 |
+
|
| 26 |
+
**Average Scores**
|
| 27 |
+
|
| 28 |
+
| model | score |
|
| 29 |
+
|----------------|----------|
|
| 30 |
+
| gpt-4 | 8.990625 |
|
| 31 |
+
| gpt-3.5-turbo | 7.943750 |
|
| 32 |
+
| claude-v1 | 7.900000 |
|
| 33 |
+
| LexGPT-V2 | 7.196875 |
|
| 34 |
+
| vicuna-13b-v1.3| 6.387500 |
|