Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Step 3.7 Flash
StepFun
- K-EXAONE 2.0 0803
LG AI Research
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Step 3.7 Flash StepFun | K-EXAONE 2.0 0803 LG AI Research | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 19.5 | Best: 19.7 | |
| Coding | 39.6 | Best: 40.6 | |
| Speed | 185 t/s | — | |
| TTFT | 2.53 s | — | |
| Input · $ / 1M tokens | $0.20 | — | |
| Output · $ / 1M tokens | $1.15 | — | |
| Context window | 262K | — | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes |
Intelligence
- Step 3.7 Flash
- 19.5
- K-EXAONE 2.0 0803
- Best: 19.7
Coding
- Step 3.7 Flash
- 39.6
- K-EXAONE 2.0 0803
- Best: 40.6
Speed
- Step 3.7 Flash
- 185 t/s
- K-EXAONE 2.0 0803
- —
TTFT
- Step 3.7 Flash
- 2.53 s
- K-EXAONE 2.0 0803
- —
Input · $ / 1M tokens
- Step 3.7 Flash
- $0.20
- K-EXAONE 2.0 0803
- —
Output · $ / 1M tokens
- Step 3.7 Flash
- $1.15
- K-EXAONE 2.0 0803
- —
Context window
- Step 3.7 Flash
- 262K
- K-EXAONE 2.0 0803
- —
Reasoning
- Step 3.7 Flash
- Yes
- K-EXAONE 2.0 0803
- Yes
Open weights
- Step 3.7 Flash
- Yes
- K-EXAONE 2.0 0803
- 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.
- Step 3.7 Flash19.5 · $0.438
Not plotted for lack of data on these axes: K-EXAONE 2.0 0803.