DeepSeek-R1-0528 Throughput
DeepSeek-R1 Throughput enables cost-effective access to advanced reasoning capabilities without compromising quality
This model is not available on Together’s Serverless API.
Pick a supported alternative from the Model Library.
Performance benchmarks
Model | AIME 2025 | GPQA Diamond | HLE | LiveCodeBench | MATH500 | SWE-bench verified |
|---|---|---|---|---|---|---|
DeepSeek-R1-0528 Throughput | 76.3% | 73.1% | Related open-source models | Competitor closed-source models | ||
 Claude Fable 5 | 92.6% | 53% | ||||
Claude Opus 5 | 93.2% | 53% | ||||
 GPT-5.6 Sol | 94.1% | 47% | ||||
 Grok 4.5 | 93.1% | 40% |
Related models
- TypeLLMReasoningChat
- Main use casesChatReasoning
- FeaturesJSON Mode
- Parameters684.5B
- Context length128K
- Quantization levelFP8
- External link
- CategoryChat