LLM Comparison
DeepSeek V3.2 Exp vs ERNIE 4.5 21B A3B Thinking
Side-by-side specs, pricing & capabilities · Updated April 2026
Add to comparison
2/6 modelsSame tier:
D DeepSeek V3.2 Exp | E ERNIE 4.5 21B A3B Thinking | |
|---|---|---|
| Organization | DeepSeek | Baidu |
| OpenTools Score | 48 142 | |
| Family | DeepSeek | ERNIE |
| Status | Current | Current |
| Release Date | Sep 2025 | Oct 2025 |
| Context Window | 164K tokens | 131K tokens |
| Input Price | $0.27/M tokens | $0.07/M tokens |
| Output Price | $0.41/M tokens | $0.28/M tokens |
| Capabilities | textcode | textcodeextended-thinking |
| Max Output | 66K tokens | 66K tokens |
| API Identifier | deepseek/deepseek-v3.2-exp | baidu/ernie-4.5-21b-a3b-thinking |
| Benchmarks | ||
| MMLU-Pro | 85deepseek | — |
| GPQA Diamond | 79.9deepseek | — |
| AIME 2025 | 89deepseek | — |
| HMMT 2025 | 84deepseek | — |
| SWE-bench Verified | 67.8deepseek | — |
| Terminal-Bench | 37.7deepseek | — |
| BrowseComp | 40.1deepseek | — |
| View DeepSeek V3.2 Exp | View ERNIE 4.5 21B A3B Thinking | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| ERNIE 4.5 21B A3B ThinkingCheapest | $0.07 | $0.14 | $0.21 | — |
| DeepSeek V3.2 Exp | $0.27 | $0.21 | $0.48 | +126% |
DeepSeek
DeepSeek V3.2 Exp
DeepSeek V3.2 Exp is a large language model from DeepSeek. Supports up to 163,840 token context window. Achieves 87.1% on MMLU. Available from $0.27/M input tokens.
Baidu
ERNIE 4.5 21B A3B Thinking
ERNIE 4.5 21B A3B Thinking is a large language model from Baidu. Supports up to 131,072 token context window. Available from $0.07/M input tokens.
More Comparisons
Looking for more AI models?
Browse All LLMs