| agents-on-bench-airline | Rufus-Air | – | Accuracy: 84.0 |
| agents-on-bench-retail | Rufus-Air | – | Accuracy: 85.3 |
| agents-on-bench-telecom | Rufus-Air | – | Accuracy: 93.0 |
| code-generation-on-livecodebench-v6 | Rufus-Air | – | Pass@1: 0.764 |
| code-generation-on-swe-bench-verified | Rufus-Air | – | Accuracy: 65.6 |
| code-generation-on-terminal-bench-2-1 | Rufus-Air | – | Accuracy: 42.7 |
| instruction-following-on-ifbench | Rufus-Air | – | Accuracy: 76.9 |
| instruction-following-on-ifeval | Rufus-Air | – | Prompt-level strict-accuracy: 95.4 |
| instruction-following-on-multichallenge | Rufus-Air | – | Accuracy: 65.8 |
| mathematical-reasoning-on-aime-2026 | Rufus-Air | – | Accuracy: 86.7 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Rufus-Air | – | Accuracy: 75.6 |
| science-question-answering-on-frontierscience-olympiad | Rufus-Air | – | Accuracy: 54.6 |
| science-question-answering-on-frontierscience-research | Rufus-Air | – | Accuracy: 35.1 |