Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DiffusionGemma 26B A4B
Google
- Qwen3 Coder 30B A3B Instruct
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DiffusionGemma 26B A4B | Qwen3 Coder 30B A3B Instruct Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 9.5 | Best: 9.6 | |
| Coding | 19.7 | — | |
| Math | — | 29 | |
| Speed | — | 156 t/s | |
| TTFT | — | 1.02 s | |
| Input · $ / 1M tokens | — | $0.15 | |
| Output · $ / 1M tokens | — | $0.748 | |
| Context window | 256K | Best: 262K | |
| Reasoning | Yes | No | |
| Open weights | Yes | Yes |
Intelligence
- DiffusionGemma 26B A4B
- 9.5
- Qwen3 Coder 30B A3B Instruct
- Best: 9.6
Coding
- DiffusionGemma 26B A4B
- 19.7
- Qwen3 Coder 30B A3B Instruct
- —
Math
- DiffusionGemma 26B A4B
- —
- Qwen3 Coder 30B A3B Instruct
- 29
Speed
- DiffusionGemma 26B A4B
- —
- Qwen3 Coder 30B A3B Instruct
- 156 t/s
TTFT
- DiffusionGemma 26B A4B
- —
- Qwen3 Coder 30B A3B Instruct
- 1.02 s
Input · $ / 1M tokens
- DiffusionGemma 26B A4B
- —
- Qwen3 Coder 30B A3B Instruct
- $0.15
Output · $ / 1M tokens
- DiffusionGemma 26B A4B
- —
- Qwen3 Coder 30B A3B Instruct
- $0.748
Context window
- DiffusionGemma 26B A4B
- 256K
- Qwen3 Coder 30B A3B Instruct
- Best: 262K
Reasoning
- DiffusionGemma 26B A4B
- Yes
- Qwen3 Coder 30B A3B Instruct
- No
Open weights
- DiffusionGemma 26B A4B
- Yes
- Qwen3 Coder 30B A3B Instruct
- 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.
- Qwen3 Coder 30B A3B Instruct9.6 · $0.30
Not plotted for lack of data on these axes: DiffusionGemma 26B A4B.