| computer-use-agents-on-webvoyager | Project Mariner | – | Success Rate: 83.5 |
| multi-task-language-understanding-on-mmlu-pro | Gemini 2.0 Flash Experimental | – | Accuracy: 76.4 |
| multimodal-reasoning-on-mmmu | Gemini 2.0 Flash Experimental | – | Accuracy: 70.7 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Gemini 2.0 Flash Experimental | – | Accuracy: 62.1 |
| visual-question-answering-vqa-on-vibe-eval | Gemini 2.0 Flash Experimental | – | Accuracy: 56.3 |
| zero-shot-video-question-answer-on-egoschema-fullset | Gemini 2.0 Flash Experimental | – | Accuracy: 71.5 |