| math-word-problem-solving-on-mgsm-0-shot | Llama 4 Maverick | #1 | Accuracy: 92.3 |
| math-word-problem-solving-on-mgsm-0-shot | Llama 4 Scout | #2 | Accuracy: 90.6 |
| chart-question-answering-on-chartqa | Llama 4 Maverick | #9 | 1:1 Accuracy: 90.0 |
| chart-question-answering-on-chartqa | Llama 4 Scout | #16 | 1:1 Accuracy: 88.8 |
| code-generation-on-livecodebench-v5 | Llama 4 Maverick | #14 | Pass@1: 43.4 |
| code-generation-on-livecodebench-v5 | Llama 4 Scout | #17 | Pass@1: 32.8 |
| visual-question-answering-on-docvqa-test | Llama 4 Scout | #16 | ANLS: 0.944 |
| visual-question-answering-on-docvqa-test | Llama 4 Maverick | #17 | ANLS: 0.944 |
| multimodal-reasoning-on-mmmu | Llama 4 Maverick | #19 | Accuracy: 73.4 |
| multimodal-reasoning-on-mmmu | Llama 4 Scout | #37 | Accuracy: 69.4 |
| multimodal-reasoning-on-mmmu-pro | Llama 4 Maverick | #30 | Accuracy: 59.6 |
| multimodal-reasoning-on-mmmu-pro | Llama 4 Scout | #40 | Accuracy: 52.2 |
| multi-task-language-understanding-on-mmlu-pro | Llama 4 Maverick | #42 | Accuracy: 80.5 |
| multi-task-language-understanding-on-mmlu-pro | Llama 4 Scout | #58 | Accuracy: 74.3 |
| multimodal-reasoning-on-mathvista | Llama 4 Maverick | #53 | Accuracy: 73.7 |
| multimodal-reasoning-on-mathvista | Llama 4 Scout | #62 | Accuracy: 70.7 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Llama 4 Maverick | #85 | Accuracy: 69.8 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Llama 4 Scout | #102 | Accuracy: 57.2 |