Kimi K3.1 Pro vs Step 5 Preview
Kimi K3.1 Pro scores 46.5 on the Artificial Analysis Intelligence Index, against 28.5 for Step 5 Preview. Step 5 Preview costs $1.43 per million tokens (3:1 blend), against $4 for Kimi K3.1 Pro. Step 5 Preview generates 109 t/s, against 31.3 t/s for Kimi K3.1 Pro. Both accept a context of 1M tokens.
Comparison generated from the catalogue data. Add or remove models below to refine it.
2 models compared
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Add a model · 2/4 | ||
|---|---|---|---|
| Intelligence | Best: 46.5 | 28.5 | |
| Cyber Index | Best: 64.1% | 47.7% | |
| Speed | 31.3 t/s | Best: 109 t/s | |
| TTFT | Best: 3.92 s | 15.3 s | |
| Input · $ / 1M tokens | $2×2 relative to the lowest price among the compared models | Best: $1 | |
| Output · $ / 1M tokens | $10×3.7 relative to the lowest price among the compared models | Best: $2.70 | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $3.68×1.6 relative to the lowest price among the compared models | Best: $2.35 |
Intelligence
- Kimi K3.1 Pro
- Best: 46.5
- Step 5 Preview
- 28.5
Cyber Index
- Kimi K3.1 Pro
- Best: 64.1%
- Step 5 Preview
- 47.7%
Speed
- Kimi K3.1 Pro
- 31.3 t/s
- Step 5 Preview
- Best: 109 t/s
TTFT
- Kimi K3.1 Pro
- Best: 3.92 s
- Step 5 Preview
- 15.3 s
Input · $ / 1M tokens
- Kimi K3.1 Pro
- $2×2 relative to the lowest price among the compared models
- Step 5 Preview
- Best: $1
Output · $ / 1M tokens
- Kimi K3.1 Pro
- $10×3.7 relative to the lowest price among the compared models
- Step 5 Preview
- Best: $2.70
Context window
- Kimi K3.1 Pro
- 1M
- Step 5 Preview
- 1M
Reasoning
- Kimi K3.1 Pro
- Yes
- Step 5 Preview
- Yes
Open weights
- Kimi K3.1 Pro
- Yes
- Step 5 Preview
- Yes
Cost / task
- Kimi K3.1 Pro
- $3.68×1.6 relative to the lowest price among the compared models
- Step 5 Preview
- Best: $2.35
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.
- Kimi K3.1 Pro46.5 · $3.68
- Step 5 Preview28.5 · $2.35