| agents-on-bench-telecom | Kolibri | #2 | Accuracy: 94.7 |
| agents-on-bench-airline | Kolibri | #4 | Accuracy: 76.7 |
| mathematical-reasoning-on-aime-2025 | Kolibri | #4 | Accuracy: 96.9 |
| mathematical-reasoning-on-aime-2026 | Kolibri | #4 | Accuracy: 96.0 |
| agents-on-bench-retail | Kolibri | #6 | Accuracy: 69.9 |
| question-answering-on-humanity-s-last-exam-hle | Kolibri | #26 | Accuracy: 21.5 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Kolibri | #41 | Accuracy: 84.3 |
| multi-task-language-understanding-on-mmlu-pro | Kolibri | #44 | Accuracy: 80.0 |
| code-generation-on-terminal-bench-2-1 | Kolibri (Terminus-2) | #47 | Accuracy: 27.7 |
| code-generation-on-swe-bench-verified | Kolibri (OpenCode) | #53 | Accuracy: 66.4 |
| deep-research-agents-on-browsecomp | Kolibri | #57 | Accuracy: 29.4 |
| code-generation-on-livecodebench-v6 | Kolibri | #63 | Pass@1: 0.859 |