Recent Papers / arXiv:2602.15763
GLM-5: from Vibe Coding to Agentic Engineering
Authors pending
Tasks
editResults
8 results reproduced from this paper.
Sorted instantly in-page
Results
8
SOTA rows
1
Models
2
Datasets
0
| # | Model | Vendor | Benchmark | Value | SOTA | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | GLM-5 | Zhipu AI | Tau2-Bench | 89.7% | #1 | — | source ↗ |
| 02 | GLM-5.1 | — | GPQA Diamond | 86.2% | — | source ↗ | |
| 03 | GLM-5 | Zhipu AI | GPQA Diamond | 86.0% | — | source ↗ | |
| 04 | GLM-5 | Zhipu AI | SWE-Bench Verified | 77.8% | — | source ↗ | |
| 05 | GLM-5.1 | — | BrowseComp | 68.0% | — | source ↗ | |
| 06 | GLM-5 | Zhipu AI | BrowseComp | 62.0% | — | source ↗ | |
| 07 | GLM-5.1 | — | HLE | 31.0% | — | source ↗ | |
| 08 | GLM-5 | Zhipu AI | HLE | 30.5% | — | source ↗ |
CodeSOTA extraction
Benchmark evidence
Link this paper to benchmark rows, datasets, model cards, and reproduced results as evidence is extracted.