glm-5.2
91.9%±1.6%
90.2%CI93.5%
aiqbench · LLM benchmarks
91.9%±1.6%
90.2%CI93.5%
90.9%±1.6%
89.3%CI92.5%
90.2%±1.7%
88.4%CI91.9%
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 25 | glm-5.2 | Z.ai (Zhipu AI) | Jun 2026 | $0.62 / $2.42 | 91.9% | 90.2%–93.5% | #9–49 | ||
| 32 | glm-5.3 | Z.ai (Zhipu AI) | Aug 2026 | $0.08 / $1.80 | 90.9% | 89.3%–92.5% | #18–52 | ||
| 42 | glm-5.3-flash | Z.ai (Zhipu AI) | Aug 2026 | $0.05 / $0.20 | 90.2% | 88.4%–91.9% | #26–60 | ||
| 43 | glm-5.1 | Z.ai (Zhipu AI) | Apr 2026 | $0.97 / $3.04 | 89.9% | 87.8%–92.0% | #44–75 | ||
| 57 | glm-5 | Z.ai (Zhipu AI) | Feb 2026 | $1 / $3.20 | 87.8% | 85.5%–90.2% | #57–153 |
Showing GPQA Diamond exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.