| question-answering-on-simpleqa | ERNIE-4.5-300B-A47B | #1 | Accuracy: 45.9 |
| visual-question-answering-vqa-on-mmbench-cn | ERNIE-4.5-VL-424B-A47B | #2 | Accuracy: 90.9 |
| instruction-following-on-multi-if | ERNIE-4.5-300B-A47B | #4 | Accuracy: 76.6 |
| multi-task-language-understanding-on-livebench-2024-11-25 | ERNIE-4.5-300B-A47B | #5 | Score: 68.9 |
| multi-task-language-understanding-on-c-eval | ERNIE-4.5-300B-A47B | #6 | Accuracy: 90.6 |
| arithmetic-reasoning-on-gsm8k | ERNIE-4.5-300B-A47B | #8 | Accuracy: 96.6 |
| logic-puzzle-solving-on-zebralogic | ERNIE-4.5-300B-A47B | #10 | Accuracy: 58.1 |
| object-counting-on-countbench | ERNIE-4.5-VL-424B-A47B | #16 | Accuracy: 89.0 |
| mathematical-reasoning-on-math-500 | ERNIE-4.5-300B-A47B | #17 | Accuracy: 96.4 |
| optical-character-recognition-ocr-on-ocrbench | ERNIE-4.5-VL-424B-A47B | #19 | Score: 872 |
| code-generation-on-humaneval | ERNIE-4.5-300B-A47B | #24 | Pass@1: 92.1 |
| chart-question-answering-on-chartqa | ERNIE-4.5-VL-424B-A47B | #27 | 1:1 Accuracy: 86.8 |
| multimodal-reasoning-on-mmmu-pro | ERNIE-4.5-VL-424B-A47B | #32 | Accuracy: 58.8 |
| visual-question-answering-vqa-on-realworldqa | ERNIE-4.5-VL-424B-A47B | #34 | Accuracy: 73.2 |
| multimodal-reasoning-on-mathvista | ERNIE-4.5-VL-424B-A47B | #35 | Accuracy: 78.9 |
| multimodal-reasoning-on-mmmu | ERNIE-4.5-VL-424B-A47B | #36 | Accuracy: 70.0 |
| multi-task-language-understanding-on-mmlu-pro | ERNIE-4.5-300B-A47B | #46 | Accuracy: 78.4 |
| code-generation-on-livecodebench-v6 | ERNIE-4.5-300B-A47B | #57 | Pass@1: 38.8 |
| mathematical-reasoning-on-aime24 | ERNIE-4.5-300B-A47B | #75 | Acc: 54.8 |
| mathematical-reasoning-on-aime-2025 | ERNIE-4.5-300B-A47B | #107 | Accuracy: 35.1 |