APEX-v1-extended
Extended APEX-v1 benchmark for expert-level professional tasks across finance, legal, medical, and consulting domains, scored by rubric grading.
2rows
scoreprimary metric
2026-05-06sampled
Metadata
Metrics
Score
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | zai-org/GLM-4.7 | 51.70 | GLM 4.7 z-ai-glm-4.7 | Imported | 2026-05-06 |
| 2 | zai-org/GLM-5 | 49 | GLM 5 z-ai-glm-5 | Imported | 2026-05-06 |
No matching rows.