Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen2 Instruct 72B
Alibaba
- Celeris-1
Celeris
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen2 Instruct 72B Alibaba | Celeris-1 Celeris | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 6.3 | 6.3 | |
| Coding | — | 14.4 | |
| Agentic | — | 0.7 | |
| Speed | — | 1,459 t/s | |
| TTFT | — | 0.61 s | |
| Input · $ / 1M tokens | — | $0.20 | |
| Output · $ / 1M tokens | — | $0.70 | |
| Context window | 131K | 131K | |
| Reasoning | No | No | |
| Open weights | Yes | No | |
| Cost / task | — | $0.0502 |
Intelligence
- Qwen2 Instruct 72B
- 6.3
- Celeris-1
- 6.3
Coding
- Qwen2 Instruct 72B
- —
- Celeris-1
- 14.4
Agentic
- Qwen2 Instruct 72B
- —
- Celeris-1
- 0.7
Speed
- Qwen2 Instruct 72B
- —
- Celeris-1
- 1,459 t/s
TTFT
- Qwen2 Instruct 72B
- —
- Celeris-1
- 0.61 s
Input · $ / 1M tokens
- Qwen2 Instruct 72B
- —
- Celeris-1
- $0.20
Output · $ / 1M tokens
- Qwen2 Instruct 72B
- —
- Celeris-1
- $0.70
Context window
- Qwen2 Instruct 72B
- 131K
- Celeris-1
- 131K
Reasoning
- Qwen2 Instruct 72B
- No
- Celeris-1
- No
Open weights
- Qwen2 Instruct 72B
- Yes
- Celeris-1
- No
Cost / task
- Qwen2 Instruct 72B
- —
- Celeris-1
- $0.0502
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.
- Celeris-16.3 · $0.0502
Not plotted for lack of data on these axes: Qwen2 Instruct 72B.