| agents-on-bench-telecom | K-EXAONE (236B, reasoning) | #7 | Accuracy: 73.5 |
| mathematical-reasoning-on-aime-2025 | K-EXAONE (236B, reasoning) | #15 | Accuracy: 92.8 |
| code-generation-on-livecodebench-v6 | K-EXAONE (236B, reasoning) | #16 | Pass@1: 80.7 |
| instruction-following-on-ifbench | K-EXAONE (236B, reasoning) | #23 | Accuracy: 67.3 |
| multi-task-language-understanding-on-mmlu-pro | K-EXAONE (236B, reasoning) | #26 | Accuracy: 83.8 |
| deep-research-agents-on-browsecomp | K-EXAONE (236B, reasoning) | #51 | Accuracy: 31.4 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | K-EXAONE (236B, reasoning) | #57 | Accuracy: 79.1 |
| code-generation-on-swe-bench-verified | K-EXAONE (236B, reasoning) (mini-SWE-agent) | #75 | Accuracy: 49.4 |