# mai-experimental-test vs GLM-5.3 - AI Model Comparison

- Page: https://opencode.ai/data/compare/unknown/mai-experimental-test/zhipuai/glm-5-3
- Updated: 2026-10-02T09:36:21.000Z

|  | mai-experimental-test | GLM-5.3 |
| --- | --- | --- |
| Lab | Unknown | Zhipu |
| Context window | - | 1M |
| Max output | - | 131K |
| Input modalities | - | text |
| Reasoning | - | Yes |
| Tool calling | - | Yes |
| Open weights | - | Yes |
| Release date | - | 2026-08-14 |
| Input price per 1M tokens | - | $1.40 |
| Output price per 1M tokens | - | $4.40 |
| Cached input price per 1M tokens | - | $0.26 |
| OpenCode tokens: past 2 months | 203B | 1.4T |
| Share of all tokens | 0.0% | 0.2% |
| Rank by tokens last week | #19 | #23 |
| Unique users | 53K | 325K |
| Weekly retention | - | 53.6% |

Model pages: [mai-experimental-test](https://opencode.ai/data/unknown/mai-experimental-test.md), [GLM-5.3](https://opencode.ai/data/zhipuai/glm-5-3.md)

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.