Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude 4 Sonnet (Reasoning)
Anthropic
- JT-35B-Flash
China Mobile
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude 4 Sonnet (Reasoning) Anthropic | JT-35B-Flash China Mobile | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 18.9 | 18.7 | |
| Coding | 37.6 | — | |
| Math | 74.3 | — | |
| Context window | Best: 1M | 256K | |
| Reasoning | Yes | No | |
| Open weights | No | No |
Intelligence
- Claude 4 Sonnet (Reasoning)
- Best: 18.9
- JT-35B-Flash
- 18.7
Coding
- Claude 4 Sonnet (Reasoning)
- 37.6
- JT-35B-Flash
- —
Math
- Claude 4 Sonnet (Reasoning)
- 74.3
- JT-35B-Flash
- —
Context window
- Claude 4 Sonnet (Reasoning)
- Best: 1M
- JT-35B-Flash
- 256K
Reasoning
- Claude 4 Sonnet (Reasoning)
- Yes
- JT-35B-Flash
- No
Open weights
- Claude 4 Sonnet (Reasoning)
- No
- JT-35B-Flash
- No
Each reasoning level remains a separate configuration.