Claim · agents

Z-Ai/GLM 4.7on Terminal-Bench 2

— to — the range across every scoreable measurement we hold

— points between the highest and the lowest

— the number the board uses: the lower median, a real row with its own provenance

0 declared configurations, from 0 runners

All 0 scoreable measurements here come from one runner under one declared configuration, so nothing on this page explains why they differ. That is the finding.

Vendor numbers nobody has independently checked

Published by the model's own maker, on a variant of this benchmark that no independent party we hold has run. They are recorded and they are shown. They can never move a rank.

Variant	Claimed
no variant stated	33.4

Every measurement

2 rows. Best first. the board takes the LOWER MEDIAN of the scoreable measurements, which is a real row with its own interval and provenance rather than an interpolated average. a vendor self-report is shown beside the independent numbers and is never one of them; it cannot move a rank.

Score	Provenance	Configuration	Who ran it	Where to check it
33.4 / 100 as published: 33.4%	UNATTRIBUTED shown, never scored	glm-4.7 harness Terminus 2	Terminal-Bench via Epoch AI 2026-01-28 CC-BY-4.0	NO_URL2026-08-30 benchmark leaderboard the leaderboard for this benchmark, not a link to this row
33.3 / 100 as published: 33.3%	UNATTRIBUTED shown, never scored	glm-4.7 harness Crux	Terminal-Bench via Epoch AI 2026-02-08 CC-BY-4.0	NO_URL2026-08-30 benchmark leaderboard the leaderboard for this benchmark, not a link to this row

← The Forge Rankings

Snapshot 2026-08-30-62e4e85f043b, manifest dc46131315046f1e, as of 2026-08-30. where only one party has measured a model on a benchmark, this page says so rather than presenting a single number as a reconciliation.