Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Celeris-1
Celeris
- EXAONE 4.0 32B (Non-reasoning)
LG AI Research
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Celeris-1 Celeris | EXAONE 4.0 32B (Non-reasoning) LG AI Research | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 6.3 | 6.3 | |
| Coding | 14.4 | — | |
| Math | — | 39.3 | |
| Agentic | 0.7 | — | |
| Speed | 1,663 t/s | — | |
| TTFT | 0.55 s | — | |
| Input · $ / 1M tokens | $0.20 | — | |
| Output · $ / 1M tokens | $0.70 | — | |
| Context window | Best: 1M | 131K | |
| Reasoning | No | No | |
| Open weights | No | Yes | |
| Cost / task | $0.0502 | — |
Intelligence
- Celeris-1
- 6.3
- EXAONE 4.0 32B (Non-reasoning)
- 6.3
Coding
- Celeris-1
- 14.4
- EXAONE 4.0 32B (Non-reasoning)
- —
Math
- Celeris-1
- —
- EXAONE 4.0 32B (Non-reasoning)
- 39.3
Agentic
- Celeris-1
- 0.7
- EXAONE 4.0 32B (Non-reasoning)
- —
Speed
- Celeris-1
- 1,663 t/s
- EXAONE 4.0 32B (Non-reasoning)
- —
TTFT
- Celeris-1
- 0.55 s
- EXAONE 4.0 32B (Non-reasoning)
- —
Input · $ / 1M tokens
- Celeris-1
- $0.20
- EXAONE 4.0 32B (Non-reasoning)
- —
Output · $ / 1M tokens
- Celeris-1
- $0.70
- EXAONE 4.0 32B (Non-reasoning)
- —
Context window
- Celeris-1
- Best: 1M
- EXAONE 4.0 32B (Non-reasoning)
- 131K
Reasoning
- Celeris-1
- No
- EXAONE 4.0 32B (Non-reasoning)
- No
Open weights
- Celeris-1
- No
- EXAONE 4.0 32B (Non-reasoning)
- Yes
Cost / task
- Celeris-1
- $0.0502
- EXAONE 4.0 32B (Non-reasoning)
- —
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: EXAONE 4.0 32B (Non-reasoning).