Update README.md
Browse files
README.md
CHANGED
|
@@ -48,7 +48,7 @@ To compare the performance of Ring-lite-2507 and Ring-lite, we evaluate the two
|
|
| 48 |
| :-------------: | :---------------: | :-----------: | :-------------------: |
|
| 49 |
| MMLU-Pro (EM) | 71.52 | 72.50 | 72.56 |
|
| 50 |
| GPQA-Diamond (Pass@1) | 68.24 | 69.35 | 62.00 |
|
| 51 |
-
| SuperGPQA (EM) | 36.21 | 39.57 |
|
| 52 |
| Phybench (Pass@1) | 25.80 | 28.51 | 22.14 |
|
| 53 |
|
| 54 |
|
|
@@ -56,7 +56,7 @@ To compare the performance of Ring-lite-2507 and Ring-lite, we evaluate the two
|
|
| 56 |
|
| 57 |
| **Benchmark** | **Ring-lite-2507** | **Ring-lite-2506** | **Qwen3-8B-Thinking**
|
| 58 |
| :-------------: | :---------------: | :-----------: | :-------------------: |
|
| 59 |
-
| MATH-500 (Pass@1) | 97.60 |
|
| 60 |
| CNMO 2024 (Pass@1) | 76.91 | 77.78 | 75.09 |
|
| 61 |
| AIME 2024 (Pass@1) | 79.69 | 84.06 | 79.27 |
|
| 62 |
| AIME 2025 (Pass@1) | 74.06 | 79.74 | 71.25 |
|
|
|
|
| 48 |
| :-------------: | :---------------: | :-----------: | :-------------------: |
|
| 49 |
| MMLU-Pro (EM) | 71.52 | 72.50 | 72.56 |
|
| 50 |
| GPQA-Diamond (Pass@1) | 68.24 | 69.35 | 62.00 |
|
| 51 |
+
| SuperGPQA (EM) | 36.21 | 39.57 | 43.07 |
|
| 52 |
| Phybench (Pass@1) | 25.80 | 28.51 | 22.14 |
|
| 53 |
|
| 54 |
|
|
|
|
| 56 |
|
| 57 |
| **Benchmark** | **Ring-lite-2507** | **Ring-lite-2506** | **Qwen3-8B-Thinking**
|
| 58 |
| :-------------: | :---------------: | :-----------: | :-------------------: |
|
| 59 |
+
| MATH-500 (Pass@1) | 97.60 | 97.95 | 97.30 |
|
| 60 |
| CNMO 2024 (Pass@1) | 76.91 | 77.78 | 75.09 |
|
| 61 |
| AIME 2024 (Pass@1) | 79.69 | 84.06 | 79.27 |
|
| 62 |
| AIME 2025 (Pass@1) | 74.06 | 79.74 | 71.25 |
|