Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek V3.2 Exp (Reasoning)
DeepSeek
- Step 3.5 Flash
StepFun
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek V3.2 Exp (Reasoning) DeepSeek | Step 3.5 Flash StepFun | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 16.6 | 16.6 | |
| Math | 87.7 | — | |
| Speed | — | 138 t/s | |
| TTFT | — | 3.3 s | |
| Input · $ / 1M tokens | $0.28×2.8 relative to the lowest price among the compared models | Best: $0.10 | |
| Output · $ / 1M tokens | $0.42×1.4 relative to the lowest price among the compared models | Best: $0.30 | |
| Context window | 128K | Best: 256K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes |
Intelligence
- DeepSeek V3.2 Exp (Reasoning)
- 16.6
- Step 3.5 Flash
- 16.6
Math
- DeepSeek V3.2 Exp (Reasoning)
- 87.7
- Step 3.5 Flash
- —
Speed
- DeepSeek V3.2 Exp (Reasoning)
- —
- Step 3.5 Flash
- 138 t/s
TTFT
- DeepSeek V3.2 Exp (Reasoning)
- —
- Step 3.5 Flash
- 3.3 s
Input · $ / 1M tokens
- DeepSeek V3.2 Exp (Reasoning)
- $0.28×2.8 relative to the lowest price among the compared models
- Step 3.5 Flash
- Best: $0.10
Output · $ / 1M tokens
- DeepSeek V3.2 Exp (Reasoning)
- $0.42×1.4 relative to the lowest price among the compared models
- Step 3.5 Flash
- Best: $0.30
Context window
- DeepSeek V3.2 Exp (Reasoning)
- 128K
- Step 3.5 Flash
- Best: 256K
Reasoning
- DeepSeek V3.2 Exp (Reasoning)
- Yes
- Step 3.5 Flash
- Yes
Open weights
- DeepSeek V3.2 Exp (Reasoning)
- Yes
- Step 3.5 Flash
- Yes
Each reasoning level remains a separate configuration.
Score and cost
Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.
- DeepSeek V3.2 Exp (Reasoning)16.6 · $0.315
- Step 3.5 Flash16.6 · $0.15