Update README.md

README.md

@@ -46,14 +46,16 @@ We also found that increasing the number of topics on low-length data increases
 
 # Evaluation
 
-| Model | Dataset Size | AIME_2024 | MATH_500 |
-|---|---|---|---|
-| o1-Preview | - | 40.0 | 81.4 |
-| DeepSeek-R1-Distill-Qwen-32B | 800k | 72.6 | 94.3 |
-| OpenThinker-32B | 114k | 66.0 | 90.6 |
-| DeepSeek-R1 | >800K | 79.8 | 97.3 |
-| s1.1-32B | 1K | 56.0(56.7) | 94.4(95.4) |
-| LONG1 | 1K | 63.3 | 95.6 |
+| Model | Dataset Size | MATH_500 | AIME_2024 | AIME_2025 | GPQA_Diamond |
+|---|---|---|---|---|---|
+| s1-32B | 1k | 92.6 | 50.0 | 26.7 | 56.6 |
+| s1.1-32B | 1k | 89.0 | 64.7 | 49.3 | 60.1 |
+| LIMO | 0.8k | <u>94.8</u> | 57.1 | 49.3 | <u>66.7</u> |
+| OpenThinker-32B | 114k | 90.6 | <u>66.0</u> | <u>53.3</u> | 61.6 |
+| DeepSeek-R1-Distill-Qwen-32B | 800K | 93.0 | **72.6** | **55.9** | 62.1 |
+| Long1-32B | 1K | **95.6** | 50.7 | <u>53.3</u> | **71.1** |
+
+Performance comparison of different models across multiple reasoning benchmarks (pass@1). The best results for each benchmark are highlighted in bold, with the second-best underlined. The data for s1 does not use budget forcing, and the data for s1.1 that does not use budget forcing comes from Open Thoughts
 
 
 # Uses