LMArena community-submitted pairwise comparisons. The screenshot reports rank 11 overall, rank spread 8–26, score 1452 ±11, and 2,875 votes; snapshot date and model-serving details are not stated.
条件
LMArena community-submitted pairwise comparisons. The screenshot reports rank 11 overall, rank spread 8–26, score 1452 ±11, and 2,875 votes; snapshot date and model-serving details are not stated. Rank 11 is retained as metadata; the numeric result is the Elo score 1452.
GLM-5 · LMArena Text (GLM-5固定v2报告/模型卡;报告快照日期未注明) 1452 Elo · Attachment evidence (ev-gm5-glm-5-lmarena-text-arena-elo-1)
Official source for LMArena Text · GLM-5固定v2报告/模型卡;报告快照日期未注明 in GLM-5. GLM-5 · 报告与固定模型卡 · 1452 Elo. See “GLM-5: from Vibe Coding to Agentic Engineering” at PDF p.3;Figure 3, left panel;相关协议见附录B.2. Evidence ev-gm5-glm-5-lmarena-text-arena-elo-1.
GLM-5 · LMArena Text (GLM-5固定v2报告/模型卡;报告快照日期未注明), configuration GLM-5 · 报告与固定模型卡, Elo rating 1452 Elo (exact score publication date unconfirmed). See “GLM-5: from Vibe Coding to Agentic Engineering” at PDF p.3;Figure 3, left panel;相关协议见附录B.2. View score conditions
Figure 3: On LMArena, GLM-5 is the #1 open model in both Text Arena and Code Arena.
Rank 11 | Rank Spread 8–26 | glm-5 | Score 1452 ±11 | Votes 2,875
GLM-5 · LMArena Text (GLM-5固定v2报告/模型卡;报告快照日期未注明), configuration GLM-5 · 报告与固定模型卡, Elo rating 1452 Elo (exact score publication date unconfirmed). Official source: GLM-5: from Vibe Coding to Agentic Engineering (Attachment, arXiv:2602.15763v2;40页全文、相关图表及附录方法已核读;2026-02-24修订。Base、训练消融与前代不归入GLM-5产品。), PDF p.3;Figure 3, left panel;相关协议见附录B.2, https://arxiv.org/pdf/2602.15763v2#page=3. Benchlog https://benchlog.lekshome.cc/evidence/glm-5/ev-gm5-glm-5-lmarena-text-arena-elo-1/?lang=en
LMArena community-submitted pairwise comparisons. The screenshot reports rank 11 overall, rank spread 8–26, score 1452 ±11, and 2,875 votes; snapshot date and model-serving details are not stated.
Conditions
LMArena community-submitted pairwise comparisons. The screenshot reports rank 11 overall, rank spread 8–26, score 1452 ±11, and 2,875 votes; snapshot date and model-serving details are not stated. Rank 11 is retained as metadata; the numeric result is the Elo score 1452.