Update README.md
Browse files
README.md
CHANGED
|
@@ -101,7 +101,6 @@ This SFT approach enables Alpie-Core to deliver reliable, aligned, and context-a
|
|
| 101 |
|
| 102 |
### SWE-Bench Verified Performance
|
| 103 |
|
| 104 |
-

|
| 105 |
|
| 106 |
| Rank | Model | Accuracy (%) | Performance vs Alpie |
|
| 107 |
|------|-------|-------------|---------------------|
|
|
@@ -113,6 +112,8 @@ This SFT approach enables Alpie-Core to deliver reliable, aligned, and context-a
|
|
| 113 |
| 6 | DeepSeek R1 | 49.2 | Below Alpie |
|
| 114 |
| 7 | Devstral | 46.8 | Below Alpie |
|
| 115 |
|
|
|
|
|
|
|
| 116 |
### Humanity's Last Exam Leaderboard Performance
|
| 117 |
|
| 118 |
| Rank | Model | Accuracy (%) | Performance vs Alpie |
|
|
|
|
| 101 |
|
| 102 |
### SWE-Bench Verified Performance
|
| 103 |
|
|
|
|
| 104 |
|
| 105 |
| Rank | Model | Accuracy (%) | Performance vs Alpie |
|
| 106 |
|------|-------|-------------|---------------------|
|
|
|
|
| 112 |
| 6 | DeepSeek R1 | 49.2 | Below Alpie |
|
| 113 |
| 7 | Devstral | 46.8 | Below Alpie |
|
| 114 |
|
| 115 |
+

|
| 116 |
+
|
| 117 |
### Humanity's Last Exam Leaderboard Performance
|
| 118 |
|
| 119 |
| Rank | Model | Accuracy (%) | Performance vs Alpie |
|