Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Gemma 4 E4B (Reasoning)
Google
- Devstral Medium
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Gemma 4 E4B (Reasoning) | Devstral Medium Mistral | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 8.9 | Best: 9 | |
| Coding | 9.4 | — | |
| Math | — | 4.7 | |
| Speed | 41.7 t/s | — | |
| TTFT | 0.96 s | — | |
| Input · $ / 1M tokens | $0.020 | — | |
| Output · $ / 1M tokens | $0.10 | — | |
| Context window | 128K | Best: 256K | |
| Reasoning | Yes | No | |
| Open weights | Yes | No | |
| Cost / task | $0.0082 | — |
Intelligence
- Gemma 4 E4B (Reasoning)
- 8.9
- Devstral Medium
- Best: 9
Coding
- Gemma 4 E4B (Reasoning)
- 9.4
- Devstral Medium
- —
Math
- Gemma 4 E4B (Reasoning)
- —
- Devstral Medium
- 4.7
Speed
- Gemma 4 E4B (Reasoning)
- 41.7 t/s
- Devstral Medium
- —
TTFT
- Gemma 4 E4B (Reasoning)
- 0.96 s
- Devstral Medium
- —
Input · $ / 1M tokens
- Gemma 4 E4B (Reasoning)
- $0.020
- Devstral Medium
- —
Output · $ / 1M tokens
- Gemma 4 E4B (Reasoning)
- $0.10
- Devstral Medium
- —
Context window
- Gemma 4 E4B (Reasoning)
- 128K
- Devstral Medium
- Best: 256K
Reasoning
- Gemma 4 E4B (Reasoning)
- Yes
- Devstral Medium
- No
Open weights
- Gemma 4 E4B (Reasoning)
- Yes
- Devstral Medium
- No
Cost / task
- Gemma 4 E4B (Reasoning)
- $0.0082
- Devstral Medium
- —
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.
- Gemma 4 E4B (Reasoning)8.9 · $0.0082
Not plotted for lack of data on these axes: Devstral Medium.