CompareAI models
- Hy4 previewTencentHollow points use fallbacks · hover for details
- GLM-5.1ZhipuHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
| Model | Reasoning | Coding | Cost efficiency | Context window | Multimodal | Tool use |
|---|---|---|---|---|---|---|
| Hy4 preview | 50/100 — Reasoning supported; no comparable benchmark | 50/100 — No data; neutral placeholder | 42/100 | 87/100 | 0/100 | 50/100 — Tool calling supported; no comparable benchmark |
| GLM-5.1 | 50/100 — Reasoning supported; no comparable benchmark | 87/100 | 34/100 | 42/100 | 0/100 | 45/100 |
Overview
Author
Context length
1M
200K
Reasoning
True
True
Input modalities
Text
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.96/ 1M
$1.40/ 1M
Output
$2.88/ 1M
$4.40/ 1M
Cached input
$0.05/ 1M
$0.26/ 1M
MomentumLast 2 mo
Unique users
36K
96K
Completed sessions
80,630
100,588
Token share
0.04%
0.02%
Tokens
312B+100%
175B-73%
AUG 4SEP 28
AUG 4SEP 28
RetentionWeek 1
Returning users
54.9%1.3K user-weeks
53.8%3.4K user-weeks
Related comparisons. Other model pairs to check.