Mungert/GLM-4.7-Flash-GGUF
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| GPQA | reasoning | 75.2 | GPQA | medium | | GPQA | 75.2 | 73.4 | 71.5 | |
| SWE-bench Verified | swe | 59.2 | SWE-bench Verified | medium | | SWE-bench Verified | 59.2 | 22.0 | 34.0 | |
| BrowseComp | agentic | 42.8 | BrowseComp | medium | | BrowseComp | 42.8 | 2.29 | 28.3 | |
| Humanity's Last Exam | knowledge | 14.4 | HLE | medium | | HLE | 14.4 | 9.8 | 10.9 | |
none scraped.