Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Llama 3.1 Tulu3 405B
Allen Institute for AI
- LFM2.5-8B-A1B
Liquid AI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Llama 3.1 Tulu3 405B Allen Institute for AI | LFM2.5-8B-A1B Liquid AI | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 7.2 | 7.2 | |
| Context window | Best: 128K | 33K | |
| Reasoning | No | Yes | |
| Open weights | Yes | Yes |
Intelligence
- Llama 3.1 Tulu3 405B
- 7.2
- LFM2.5-8B-A1B
- 7.2
Context window
- Llama 3.1 Tulu3 405B
- Best: 128K
- LFM2.5-8B-A1B
- 33K
Reasoning
- Llama 3.1 Tulu3 405B
- No
- LFM2.5-8B-A1B
- Yes
Open weights
- Llama 3.1 Tulu3 405B
- Yes
- LFM2.5-8B-A1B
- Yes
Each reasoning level remains a separate configuration.