| code-generation-on-multipl-e | Laguna XS.2 | #14 | Accuracy: 58.4 |
| code-generation-on-swe-bench-verified | Laguna M.1 (pool) | #25 | Accuracy: 74.6 |
| code-generation-on-swe-bench-verified | Laguna XS.2 (pool) | #43 | Accuracy: 69.9 |
| code-generation-on-swe-bench-multilingual | Laguna M.1 (pool) | #28 | Accuracy: 63.1 |
| code-generation-on-swe-bench-multilingual | Laguna XS.2 (pool) | #32 | Accuracy: 57.7 |
| code-generation-on-swe-bench-pro | Laguna M.1 | #34 | Resolved: 49.2 |
| code-generation-on-swe-bench-pro | Laguna XS.2 | #38 | Resolved: 46.3 |
| math-word-problem-solving-on-math | Laguna XS.2 | #57 | Accuracy: 58.8 |
| multi-task-language-understanding-on-mmlu-pro | Laguna XS.2 | #108 | Accuracy: 53.0 |
| arithmetic-reasoning-on-gsm8k | Laguna XS.2 | #124 | Accuracy: 84.2 |