Z.ai · open weights on Arena · first on Arena 22 December 2025

glm-4.7

40 days for open weights to match claude-sonnet-4-5-20250929-thinking-32k

This open-weights model matched the score of claude-sonnet-4-5-20250929-thinking-32k in WebDev 40 days after claude-sonnet-4-5-20250929-thinking-32k took first place.

Embed

Who held first place

<iframe src="https://jesseahawkins.com/frontier/embed/" title="Frontier: who held first place on each Arena leaderboard, and for how long" width="100%" height="560" style="border:0;max-width:100%" loading="lazy"></iframe>

Credits LMArena.

The open-weights catch-up

<iframe src="https://jesseahawkins.com/frontier/embed/catch-up/" title="Frontier: the days until open weights matched each closed leader" width="100%" height="900" style="border:0;max-width:100%" loading="lazy"></iframe>

Credits LMArena.

The saturation clock

<iframe src="https://jesseahawkins.com/frontier/embed/clock/" title="Frontier: the days from each benchmark’s release to a model at 90%" width="100%" height="640" style="border:0;max-width:100%" loading="lazy"></iframe>

Credits Epoch AI.

Each frame links back to its page. Preview it.

Cite

This page

Jesse Hawkins, “glm-4.7 · Frontier”, jesseahawkins.com, data retrieved 30 Oct 2026. https://jesseahawkins.com/frontier/glm-4-7/. Data: LMArena, Arena leaderboard dataset, revision 4491b06, CC BY 4.0; Epoch AI, Capabilities & benchmarking, CC BY 4.0.

BibTeX

@misc{hawkins2026frontierglm47,
  author = {Hawkins, Jesse},
  title = {{glm-4.7 · Frontier}},
  year = {2026},
  howpublished = {\url{https://jesseahawkins.com/frontier/glm-4-7/}},
  note = {Data: LMArena, Arena leaderboard dataset, revision 4491b06, CC BY 4.0; Epoch AI, Capabilities \& benchmarking, CC BY 4.0, retrieved 2026-10-30}
}

Arena · LMArena

LMArena, "Arena leaderboard dataset", Hugging Face, revision 4491b06. https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset. CC BY 4.0.

Benchmarks · Epoch AI

Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource]. CC BY 4.0.

Download

Post on X

Text: best place 12

place 89 of 419 on 28 October 2026

1st10th

On the board: 30 December 2025 to 28 October 2026, the newest snapshot
Score: 1435 (1429–1441) on 28 October 2026 · 12,239 votes

WebDev: best place 5

place 88 of 152 on 28 October 2026

1st10th

On the board: 22 December 2025 to 28 October 2026, the newest snapshot
Score: 1435 (1423–1447) on 28 October 2026 · 3,948 votes
Matched: claude-sonnet-4-5-20250929-thinking-32k on 22 December 2025, 40 days after it took first place

Epoch AI: GLM-4.7

released 22 December 2025 · Open weights (unrestricted)

Chess Puzzles 21.0%
FrontierMath-2025-02-28-Private 2.4%
FrontierMath-Tier-4-2025-07-01-Private 0.0%
GPQA diamond 83.3%
OTIS Mock AIME 2024-2025 83.3%
SimpleQA Verified 32.2%

When each vendor retires it

every model’s dates

Amazon Bedrock 30 Mar 2027 zai.glm-4.7 · 181 days’ notice, from the deprecation on 30 Sep 2026

Sources

Arena scores come from people voting between two anonymous answers. First place is the highest score; the top two are often within each other’s margin of error. LMArena, Arena leaderboard dataset, revision 4491b06, retrieved 30 October 2026; Epoch AI, Capabilities & benchmarking, retrieved 30 October 2026. Both CC BY 4.0. Retirement dates: each vendor’s own deprecation page, quoted and kept, listed with the record.