Compare Models
Select up to 4 models to compare benchmarks, pricing, and capabilities side by side.
DeepSeek
DeepSeek
DeepSeek
Add Model
MMLU
DeepSeek-V3.2
91.0
DeepSeek-Math V2
84.0
DeepSeek V4
91.5
HumanEval
DeepSeek-V3.2
92.0
DeepSeek-Math V2
0.0
DeepSeek V4
98.0
GSM8K
DeepSeek-V3.2
96.0
DeepSeek-Math V2
98.0
DeepSeek V4
96.0
GPQA
DeepSeek-V3.2
76.0
DeepSeek-Math V2
55.0
DeepSeek V4
80.0
SWE-bench
DeepSeek-V3.2
70.0
DeepSeek-Math V2
0.0
DeepSeek V4
75.0
MATH
DeepSeek-V3.2
92.0
DeepSeek-Math V2
97.5
DeepSeek V4
94.0
AIME 2025
DeepSeek-V3.2
88.0
DeepSeek-Math V2
85.0
DeepSeek V4
0.0
LiveCodeBench
DeepSeek-V3.2
0.0
DeepSeek-Math V2
0.0
DeepSeek V4
86.0
| Model | Input | Output | Blended* |
|---|---|---|---|
DeepSeek-V3.2 | $0.28 | $0.42 | $0.35 |
DeepSeek-Math V2 | $0.27 | $1.10 | $0.69 |
DeepSeek V4 | $0.10 | $0.40 | $0.25 |
*Blended = average of input and output price
| Spec | DeepSeek-V3.2 | DeepSeek-Math V2 | DeepSeek V4 |
|---|---|---|---|
| Context Window | 128K | 128K | 1.0M |
| Max Output | 16K | N/A | 16K |
| TTFT | 300ms | N/A | 400ms |
| Speed | 90 tok/s | N/A | 80 tok/s |
| Parameters | 685B (37B active) | 671B total / 37B active | 1T (estimated) |
| Architecture | Transformer (MoE) | MoE Transformer | Transformer (MoE) + Innovations |
| Open Source | Yes | Yes | Yes |
| Tier | frontier | frontier | frontier |
Quick Verdict
Best Performance
DeepSeek V4
Best Value
DeepSeek V4
Fastest
DeepSeek-V3.2