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

Latest Results

Rows ranked by the source leaderboard rank.

Rank Subject Score Model Match Provenance Sampled
1 zai-org/GLM-4.7 51.70 GLM GLM 4.7
z-ai-glm-4.7
Imported 2026-05-06
2 zai-org/GLM-5 49 GLM GLM 5
z-ai-glm-5
Imported 2026-05-06