GLM-4.5 (Reasoning)
83.5%
no interval published
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 47 min47 minutes ago
All sources syncing normally
- Arena · Text· 1 hour ago
- Arena · WebDev· 1 hour ago
- Arena · Vision· 1 hour ago
- Arena · Agent· 1 hour ago
- GPQA Diamond· 47 minutes ago
- SWE-bench· 47 minutes ago
- Terminal-Bench· 47 minutes ago
- ARC-AGI-2· 47 minutes ago
Filter by org:
Released:
INTELLECT-3 (Based on GLM-4.5-Air)
82.2%
no interval published
GLM-4.5-Air
81.5%
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 41 | GLM-4.5 (Reasoning) | zai | Jul 2025 | $0.60 / $2.20 | 83.5% | — | #108–209 | ||
| 56 | INTELLECT-3 (Based on GLM-4.5-Air) | prime-intellect | Oct 2026 | — | 82.2% | — | #150–397 | ||
| 67 | GLM-4.5-Air | zai | Jul 2025 | $0.13 / $0.85 | 81.5% | — | #138–416 | ||
| 102 | GLM-4.5V (Reasoning) | zai | Aug 2025 | $0.60 / $1.80 | 78.8% | — | #161–490 |
Showing MMLU-Pro (Artificial Analysis) exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.