Model Comparator
Compare up to four models using the same criteria.
2 models compared
- EXAONE 4.5 33B (Reasoning)
LG AI Research
- Apriel-v1.6-15B-Thinker
ServiceNow
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | EXAONE 4.5 33B (Reasoning) LG AI Research | Apriel-v1.6-15B-Thinker ServiceNow | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 13.2 | Best: 13.4 | |
| Coding | 23.6 | — | |
| Math | — | 88 | |
| Context window | Best: 262K | 128K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes |
Intelligence
- EXAONE 4.5 33B (Reasoning)
- 13.2
- Apriel-v1.6-15B-Thinker
- Best: 13.4
Coding
- EXAONE 4.5 33B (Reasoning)
- 23.6
- Apriel-v1.6-15B-Thinker
- —
Math
- EXAONE 4.5 33B (Reasoning)
- —
- Apriel-v1.6-15B-Thinker
- 88
Context window
- EXAONE 4.5 33B (Reasoning)
- Best: 262K
- Apriel-v1.6-15B-Thinker
- 128K
Reasoning
- EXAONE 4.5 33B (Reasoning)
- Yes
- Apriel-v1.6-15B-Thinker
- Yes
Open weights
- EXAONE 4.5 33B (Reasoning)
- Yes
- Apriel-v1.6-15B-Thinker
- Yes
Each reasoning level remains a separate configuration.