Models with strong MATH / GSM8K scores. In practice these overlap heavily with Reasoning models — Chinese math specialists often ship as a reasoning-mode variant of a general model.
| Model | Creator | Context | Open weight | Tags |
|---|---|---|---|---|
| Yi-1.5-34B-Chat | 01.AI | 4K | Yes | text-generation · conversational · instruction-following |
| Qwen 2.5 Max | Alibaba Cloud | 33K | — | chat · reasoning · code |
| DeepSeek V3.1 | DeepSeek | 33K | Yes | chat · reasoning · code |
| R1 | DeepSeek | 64K | Yes | reasoning · math · coding |
Fast Pivot — Access hundreds of AI models from a single API — competitive pricing, reliable uptime, enterprise-grade infrastructure.