GLM-5 · BrowseComp(GLM-5固定v2报告/模型卡;with context management),GLM-5 · 报告与固定模型卡配置,Reported score 75.9(具体成绩公布时间未确认)。见《GLM-5 official model card (fixed revision)》Hugging Face model card Benchmark table。 查看成绩条件
| | GLM-5 | GLM-4.7 | DeepSeek-V3.2 | Kimi K2.5 | Claude Opus 4.5 | Gemini 3 Pro | GPT-5.2 (xhigh) |
| BrowseComp (w/ Context Manage) | 75.9 | 67.5 | 67.6 | 74.9 | 67.8 | 59.2 | 65.8 |
* **BrowserComp**: Without context management, we retain details from the most recent 5 turns. With context management, we use the same discard-all strategy as DeepSeek-v3.2 and Kimi K2.5.
The report's section 4.2.4 describes hybrid Hierarchical Context Management (keep-recent k=5 plus discard-all at T=32k), while the appendix and HF card footnote describe the context-managed setting as the same discard-all strategy used by DeepSeek-V3.2 and Kimi K2.5. The exact final-run protocol is therefore ambiguous.
条件
The report's section 4.2.4 describes hybrid Hierarchical Context Management (keep-recent k=5 plus discard-all at T=32k), while the appendix and HF card footnote describe the context-managed setting as the same discard-all strategy used by DeepSeek-V3.2 and Kimi K2.5. The exact final-run protocol is therefore ambiguous. Retained as candidate because the official sources conflict on the context-management protocol.
GLM-5 · BrowseComp (GLM-5固定v2报告/模型卡;with context management) 75.9 · Main text evidence (ev-gm5-glm-5-browsecomp-context-management-2)
Official source for BrowseComp · GLM-5固定v2报告/模型卡;with context management in GLM-5. GLM-5 · 报告与固定模型卡 · 75.9. See “GLM-5 official model card (fixed revision)” at Hugging Face model card Benchmark table. Evidence ev-gm5-glm-5-browsecomp-context-management-2.
GLM-5 · BrowseComp (GLM-5固定v2报告/模型卡;with context management), configuration GLM-5 · 报告与固定模型卡, Reported score 75.9 (exact score publication date unconfirmed). See “GLM-5 official model card (fixed revision)” at Hugging Face model card Benchmark table. View score conditions
| | GLM-5 | GLM-4.7 | DeepSeek-V3.2 | Kimi K2.5 | Claude Opus 4.5 | Gemini 3 Pro | GPT-5.2 (xhigh) |
| BrowseComp (w/ Context Manage) | 75.9 | 67.5 | 67.6 | 74.9 | 67.8 | 59.2 | 65.8 |
* **BrowserComp**: Without context management, we retain details from the most recent 5 turns. With context management, we use the same discard-all strategy as DeepSeek-v3.2 and Kimi K2.5.
The report's section 4.2.4 describes hybrid Hierarchical Context Management (keep-recent k=5 plus discard-all at T=32k), while the appendix and HF card footnote describe the context-managed setting as the same discard-all strategy used by DeepSeek-V3.2 and Kimi K2.5. The exact final-run protocol is therefore ambiguous.
Conditions
The report's section 4.2.4 describes hybrid Hierarchical Context Management (keep-recent k=5 plus discard-all at T=32k), while the appendix and HF card footnote describe the context-managed setting as the same discard-all strategy used by DeepSeek-V3.2 and Kimi K2.5. The exact final-run protocol is therefore ambiguous. Retained as candidate because the official sources conflict on the context-management protocol.