Compare, 2 models
Side by side.
DeepSeek-V4.1-Flash and GLM-5.3 on every board at least two of them share. Blue marks the best in each row.
Specs
List prices, context and published output speed. Blue marks the best in each row.
| Spec | DeepSeek-V4.1-FlashDeepSeek | GLM-5.3Zhipu |
|---|---|---|
| Lab | DeepSeek | Zhipu |
| Type | Language | Language |
| Released | Sep 10, 2026 | Aug 18, 2026 |
| Input price$ per 1M tokens | $0.30 | $1.40 |
| Output price$ per 1M tokens | $1.20 | $4.40 |
| Blended price3 input tokens per output | $0.52 | $2.15 |
| Contexttokens | 1.05M | 1.05M |
| Open weights | Yes | Yes |
| Output speedTok / s | 216 | 68 |
Benchmarks
Every board where at least two of these models have a published score. Each score links to its source.
| Board | DeepSeek-V4.1-FlashDeepSeek | GLM-5.3Zhipu |
|---|---|---|
| Artificial Analysis Intelligence IndexOverall, higher is better | 40Max | 45Max |
| Epoch Capabilities IndexOverall, higher is better | 156 | 156 |
| FrontierMath Tiers 1-3Reasoning and knowledge, higher is better | 67.4%max setting | 68.8%max setting |
| GPQA DiamondReasoning and knowledge, higher is better | 89.8%max setting | 90.9%max setting |
n/a means the board has not published a score for that model.