Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Solar Pro 3
Upstage
- DeepSeek R1 Distill Qwen 14B
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Solar Pro 3 Upstage | DeepSeek R1 Distill Qwen 14B DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 7.8 | 7.8 | |
| Coding | 16.2 | — | |
| Math | — | 55.7 | |
| Agentic | 1.4 | — | |
| Speed | 160 t/s | — | |
| TTFT | 1.28 s | — | |
| Input · $ / 1M tokens | $0.15 | — | |
| Output · $ / 1M tokens | $0.60 | — | |
| Context window | 128K | 128K | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | $0.0794 | — |
Intelligence
- Solar Pro 3
- 7.8
- DeepSeek R1 Distill Qwen 14B
- 7.8
Coding
- Solar Pro 3
- 16.2
- DeepSeek R1 Distill Qwen 14B
- —
Math
- Solar Pro 3
- —
- DeepSeek R1 Distill Qwen 14B
- 55.7
Agentic
- Solar Pro 3
- 1.4
- DeepSeek R1 Distill Qwen 14B
- —
Speed
- Solar Pro 3
- 160 t/s
- DeepSeek R1 Distill Qwen 14B
- —
TTFT
- Solar Pro 3
- 1.28 s
- DeepSeek R1 Distill Qwen 14B
- —
Input · $ / 1M tokens
- Solar Pro 3
- $0.15
- DeepSeek R1 Distill Qwen 14B
- —
Output · $ / 1M tokens
- Solar Pro 3
- $0.60
- DeepSeek R1 Distill Qwen 14B
- —
Context window
- Solar Pro 3
- 128K
- DeepSeek R1 Distill Qwen 14B
- 128K
Reasoning
- Solar Pro 3
- Yes
- DeepSeek R1 Distill Qwen 14B
- Yes
Open weights
- Solar Pro 3
- No
- DeepSeek R1 Distill Qwen 14B
- Yes
Cost / task
- Solar Pro 3
- $0.0794
- DeepSeek R1 Distill Qwen 14B
- —
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.
- Solar Pro 37.8 · $0.0794
Not plotted for lack of data on these axes: DeepSeek R1 Distill Qwen 14B.