glm-5.2
73.2%
no interval published
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 22 min22 minutes ago
All sources syncing normally
- Arena · Text· 7 hours ago
- Arena · WebDev· 7 hours ago
- Arena · Vision· 7 hours ago
- Arena · Agent· 7 hours ago
- GPQA Diamond· 22 minutes ago
- SWE-bench· 22 minutes ago
- Terminal-Bench· 22 minutes ago
- ARC-AGI-2· 22 minutes ago
Filter by org:
Released:
glm-5.1
70.2%
no interval published
glm-5
68.9%
no interval published
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 33 | glm-5.2 | Z.AI | Jun 2026 | $0.62 / $2.42 | 73.2% | — | #9–49 | ||
| 50 | glm-5.1 | Z.AI | Apr 2026 | $0.97 / $3.04 | 70.2% | — | #44–75 | ||
| 63 | glm-5 | Z.AI | Feb 2026 | $1 / $3.20 | 68.9% | — | #57–153 | ||
| 165 | glm-5v-turbo | Z.AI | Sep 2026 | $1.20 / $4 | 49.6% | — | #86–435 |
Showing LiveBench exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.