Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek V3 (Dec '24)
DeepSeek
- LFM2.5-2.6B
Liquid AI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek V3 (Dec '24) DeepSeek | LFM2.5-2.6B Liquid AI | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 8.5 | 8.4 | |
| Coding | Best: 23 | 7.7 | |
| Math | 26 | — | |
| Agentic | 0.8 | — | |
| Speed | 48 t/s | — | |
| TTFT | 0.94 s | — | |
| Input · $ / 1M tokens | $0.32 | — | |
| Output · $ / 1M tokens | $0.89 | — | |
| Context window | Best: 1M | 128K | |
| Reasoning | No | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $0.0198 | — |
Intelligence
- DeepSeek V3 (Dec '24)
- Best: 8.5
- LFM2.5-2.6B
- 8.4
Coding
- DeepSeek V3 (Dec '24)
- Best: 23
- LFM2.5-2.6B
- 7.7
Math
- DeepSeek V3 (Dec '24)
- 26
- LFM2.5-2.6B
- —
Agentic
- DeepSeek V3 (Dec '24)
- 0.8
- LFM2.5-2.6B
- —
Speed
- DeepSeek V3 (Dec '24)
- 48 t/s
- LFM2.5-2.6B
- —
TTFT
- DeepSeek V3 (Dec '24)
- 0.94 s
- LFM2.5-2.6B
- —
Input · $ / 1M tokens
- DeepSeek V3 (Dec '24)
- $0.32
- LFM2.5-2.6B
- —
Output · $ / 1M tokens
- DeepSeek V3 (Dec '24)
- $0.89
- LFM2.5-2.6B
- —
Context window
- DeepSeek V3 (Dec '24)
- Best: 1M
- LFM2.5-2.6B
- 128K
Reasoning
- DeepSeek V3 (Dec '24)
- No
- LFM2.5-2.6B
- Yes
Open weights
- DeepSeek V3 (Dec '24)
- Yes
- LFM2.5-2.6B
- Yes
Cost / task
- DeepSeek V3 (Dec '24)
- $0.0198
- LFM2.5-2.6B
- —
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.
- DeepSeek V3 (Dec '24)8.5 · $0.0198
Not plotted for lack of data on these axes: LFM2.5-2.6B.