Zhipu AI (Z.ai)
GLM-5.3 benchmark results
4 results on 4 benchmarks from 2 sources.
Also listed as: GLM-5.3 (Max) · glm-5.3_max · GLM-5.3 (max)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1481 | 26 | Overall, style control on; 25144 votes; 95% CI 1476–1486“GLM-5.3 (Max)” | Official leaderboard | Oct 22, 2026 |
| LMArena WebDev | 1623 | 24 | Overall; 10266 votes; 95% CI 1615–1630“GLM-5.3 (Max)” | Official leaderboard | Oct 22, 2026 |
| GPQA Diamond | 90.9% | 31 | Epoch AI run, accuracy; effort: max | Independent run | Aug 24, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 91.1% | 67 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: max | Independent run | Aug 24, 2026 |
Where GLM-5.3 ranks
Primary setting, one best-sourced score per model (official / independent first); neighbours in brackets.
| Benchmark | Score | Rank | Nearby models | #1 |
|---|---|---|---|---|
| LMArena Text | 1481 | #23 / 392 | GPT-5.5 1482 · Claude Opus 4.8 1482 · GPT-6.1 Sol 1480 · MiMo-V2.6-Pro 1480 | Gemini 4 Argon1517 |
| GPQA Diamond | 90.9% | #28 / 217 | GPT-5.2 91.4% · DeepSeek V4 Flash 0731 91.0% · Qwen3.7-Max 90.9% · DeepSeek-V4-Pro 90.9% | Gemini 4 Argon96.4% |
| LMArena WebDev | 1623 | #22 / 135 | MiMo-V2.6-Pro 1625 · Claude Fable 5 1624 · Grok 4.6 1617 · GPT-5.6 Sol (xHigh, Codex Harness) 1615 | Claude Opus 5.51807 |
| AIME (OTIS Mock AIME 2024–2025) | 91.1% | #53 / 200 | Gemini 3 Pro 91.4% · GPT-5 91.4% · Qwen 3.6 Max (Preview) 91.1% · Qwen3.6 27B 91.1% | Gemini 4 Argon100.0% |
Other Zhipu AI (Z.ai) models
Related on this site
FAQ
Where does GLM-5.3 rank best?
LMArena Text: #23 of 392 (1481); #1 there is Gemini 4 Argon (1517).
Where do these GLM-5.3 scores come from?
From Epoch AI Benchmarking Hub and LMArena leaderboard dataset. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.