| answerability-prediction-on-peerqa | Llama-3-IT-8B-8k | #3 | Macro F1: 0.3112 |
| answerability-prediction-on-peerqa | Llama-3-IT-8B-32k | #5 | Macro F1: 0.2881 |
| question-answering-on-peerqa | Llama-3-IT-8B-32k | #3 | Prometheus-2 Answer Correctness: 3.1673Rouge-L: 0.2286… |
| question-answering-on-peerqa | Llama-3-IT-8B-8k | #4 | Prometheus-2 Answer Correctness: 3.1102Rouge-L: 0.2295… |
| video-question-answering-on-perception-test-test | Llama 3-V (70B) | #4 | Accuracy: 60.8 |
| visual-question-answering-vqa-on-textvqa-val | Llama 3-V (405B) | #7 | Accuracy: 84.8 |
| multi-task-language-understanding-on-mmlu | DBRX Instruct 132B (5-shot) | #20 | Average (%): 73.7 |
| multi-task-language-understanding-on-mmlu | Llama 3.1 8B (CoT) | #23 | Average (%): 73.0 |
| visual-question-answering-on-docvqa-test | Llama 3-V (405B) | #27 | ANLS: 0.926 |
| chart-question-answering-on-chartqa | Llama 3-V (405B) | #41 | 1:1 Accuracy: 85.8 |
| multimodal-reasoning-on-mmmu | Llama 3-V (405B) | #51 | Accuracy: 64.5 |
| math-word-problem-solving-on-math | Llama 3.1 (8B, Instruct) | #78 | Accuracy: 51.9 |
| code-generation-on-humaneval | Llama 3.1 (8B, Instruct) | #82 | Pass@1: 72.6 |
| multi-task-language-understanding-on-mmlu-pro | Llama 3.1 (8B, Instruct) | #120 | Accuracy: 48.3 |
| arithmetic-reasoning-on-gsm8k | Llama 3.1 (8B, Instruct) | #125 | Accuracy: 84.5 |