| agents-on-taubench-airline | GLM-4.5 (355B) | #1 | Accuracy: 60.4 |
| agents-on-taubench-retail | GLM-4.5 (355B) | #1 | Accuracy: 79.7 |
| multi-task-language-understanding-on-mmlu | GLM-4.5 (355B) | #1 | Average (%): 90.0 |
| code-generation-on-livecodebench-v5 | GLM-4.5 (355B) | #3 | Pass@1: 72.9 |
| code-generation-on-livecodebench-v5 | GLM-4.5-Air | #6 | Pass@1: 70.7 |
| question-answering-on-simpleqa | GLM-4.5 (355B) | #4 | Accuracy: 26.4 |
| mathematical-reasoning-on-math-500 | GLM-4.5 (355B) | #5 | Accuracy: 98.2 |
| mathematical-reasoning-on-math-500 | GLM-4.5-Air | #6 | Accuracy: 98.1 |
| instruction-following-on-multichallenge | GLM-4.5 (355B) | #12 | Accuracy: 52.8 |
| code-generation-on-scicode | GLM-4.5 (355B) | #13 | Accuracy: 41.7 |
| code-generation-on-scicode | GLM-4.5-Air | #17 | Accuracy: 37.3 |
| mathematical-reasoning-on-aime24 | GLM-4.5-Air | #13 | Acc: 89.4 |
| multi-task-language-understanding-on-mmlu-pro | GLM-4.5 (355B) | #19 | Accuracy: 84.6 |
| multi-task-language-understanding-on-mmlu-pro | GLM-4.7 | #21 | Accuracy: 84.3 |
| multi-task-language-understanding-on-mmlu-pro | GLM-4.5-Air | #37 | Accuracy: 81.4 |
| question-answering-on-humanity-s-last-exam-hle | GLM-4.7 | #19 | Accuracy: 24.8 |
| question-answering-on-humanity-s-last-exam-hle | GLM-4.5 (355B) | #36 | Accuracy: 14.4 |
| question-answering-on-humanity-s-last-exam-hle | GLM-4.5-Air | #40 | Accuracy: 10.6 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | GLM-4.7 | #33 | Accuracy: 85.7 |
| code-generation-on-swe-bench-verified | GLM-4.5 (355B) (OpenHands) | #56 | Accuracy: 64.2 |
| code-generation-on-swe-bench-verified | GLM-4.5-Air (OpenHands) | #68 | Accuracy: 57.6 |
| deep-research-agents-on-browsecomp | GLM-4.5 (355B) | #58 | Accuracy: 26.4 |
| deep-research-agents-on-browsecomp | GLM-4.5-Air | #61 | Accuracy: 21.3 |