Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Step 3.5 Flash 2603
StepFun
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Step 3.5 Flash 2603 StepFun | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | Best: 17.4 | 17 | |
| Math | 48 | — | |
| Speed | 37.1 t/s | Best: 142 t/s | |
| TTFT | Best: 2.15 s | 3.33 s | |
| Input · $ / 1M tokens | $0.60×6 relative to the lowest price among the compared models | Best: $0.10 | |
| Output · $ / 1M tokens | $2.20×7.3 relative to the lowest price among the compared models | Best: $0.30 | |
| Context window | 200K | Best: 256K | |
| Reasoning | No | Yes | |
| Open weights | Yes | Yes |
Intelligence
- GLM-4.7 (Non-reasoning)
- Best: 17.4
- Step 3.5 Flash 2603
- 17
Math
- GLM-4.7 (Non-reasoning)
- 48
- Step 3.5 Flash 2603
- —
Speed
- GLM-4.7 (Non-reasoning)
- 37.1 t/s
- Step 3.5 Flash 2603
- Best: 142 t/s
TTFT
- GLM-4.7 (Non-reasoning)
- Best: 2.15 s
- Step 3.5 Flash 2603
- 3.33 s
Input · $ / 1M tokens
- GLM-4.7 (Non-reasoning)
- $0.60×6 relative to the lowest price among the compared models
- Step 3.5 Flash 2603
- Best: $0.10
Output · $ / 1M tokens
- GLM-4.7 (Non-reasoning)
- $2.20×7.3 relative to the lowest price among the compared models
- Step 3.5 Flash 2603
- Best: $0.30
Context window
- GLM-4.7 (Non-reasoning)
- 200K
- Step 3.5 Flash 2603
- Best: 256K
Reasoning
- GLM-4.7 (Non-reasoning)
- No
- Step 3.5 Flash 2603
- Yes
Open weights
- GLM-4.7 (Non-reasoning)
- Yes
- Step 3.5 Flash 2603
- 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.
- GLM-4.7 (Non-reasoning)17.4 · $1
- Step 3.5 Flash 260317 · $0.15