Claim · reasoning

GLM 5.1on IMOAnswerBench

86.8 to 91.1 the range across every scoreable measurement we hold

4.3 points between the highest and the lowest

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

2 declared configurations, from 1 runner

0 / 3 rows whose cited page still shows this figure, refetched and checked by us

All 2 scoreable measurements here come from ONE runner, so this is not a reconciliation and is not presented as one. What it shows is how far a single runner's number moves when the model is run differently.

1 of 3 cited pages no longer show the figure we publish. The page was refetched and split at its own structural boundaries, and no block that names this model carries this number. That does not make the measurement wrong: a leaderboard is a living page and a figure recorded when it was there can be gone by the time you follow the link. It does mean the citation, as printed, no longer supports the number, and this is the only place we know of that says so about its own sources.

What the vendor said, and what someone else measured

Matched on which variant of the benchmark was sat, and on nothing else: the vendor ran it on their harness and the independent party on theirs, and that difference is the comparison rather than an obstacle to it. A vendor number with no independent run of the same variant carries no delta, because a number that cannot be compared honestly must not be compared.

Variant	Vendor claims	Independently measured	Difference
no tools	83.8	86.8 from 1 run	-3.0

Every measurement

3 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
91.1 / 100 as published: 91.1%	INDEPENDENT counts toward the ranking	glm-5.1 harness NeMo Evaluator SDK effort model-card defaults variant with Python tools	NVIDIA via Model benchmark dossier facts, not expression	not checked: the page is a format we cannot read2026-08-30 research.nvidia.com
86.8 / 100 as published: 86.8%	INDEPENDENT counts toward the ranking	glm-5.1 harness NeMo Evaluator SDK effort model-card defaults variant no tools	NVIDIA via Model benchmark dossier facts, not expression	not checked: the page is a format we cannot read2026-08-30 research.nvidia.com
83.8 / 100 as published: 83.8%	CLAIMED shown, never scored	glm-5.1 harness model-card evaluation effort not disclosed variant no tools	Z.AI via Model benchmark dossier facts, not expression	checked: this figure is not on the page today2026-08-30GLM-5.1 huggingface.co

← 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.