Update README.md
Browse files
README.md
CHANGED
|
@@ -44,11 +44,11 @@ FlagEval (Libra)** is a comprehensive evaluation system and open platform for la
|
|
| 44 |
|
| 45 |
| Metrics | MiniMax-M1-80k-FlagOS-H100-CUDA | MiniMax-M1-80k-FlagOS-FlagOS |
|
| 46 |
| --------- | ------------------ | ---------------------- |
|
| 47 |
-
| liveBench | 0.489 | 0.487 |
|
| 48 |
-
| AIME | 0.667 | 0.767 |
|
| 49 |
-
| MMLU | 0.767 | 0.769 |
|
| 50 |
-
| MUSR | 0.671 | 0.689 |
|
| 51 |
-
| GPQA | 0.487 | 0.500 |
|
| 52 |
|
| 53 |
# User Guide
|
| 54 |
|
|
|
|
| 44 |
|
| 45 |
| Metrics | MiniMax-M1-80k-FlagOS-H100-CUDA | MiniMax-M1-80k-FlagOS-FlagOS |
|
| 46 |
| --------- | ------------------ | ---------------------- |
|
| 47 |
+
| liveBench-0shot@avg1 | 0.489 | 0.487 |
|
| 48 |
+
| AIME-0shot@avg1 | 0.667 | 0.767 |
|
| 49 |
+
| MMLU-5shots@avg1 | 0.767 | 0.769 |
|
| 50 |
+
| MUSR-0shot@avg1 | 0.671 | 0.689 |
|
| 51 |
+
| GPQA-0shot@avg1 | 0.487 | 0.500 |
|
| 52 |
|
| 53 |
# User Guide
|
| 54 |
|