DeepSeek: R1 0528
Analysis Summary
DeepSeek R1 0528 is a reasoning-oriented model with a strong math index but very limited coding and agentic capability. Its livecodebench score of 0.513 is moderate, but the agentic index of 1.5 and terminalbench score near zero make it unsuitable for autonomous or tool-use workflows. Instruction following is also weak, with an ifbench score of 0.199.
For businesses, this model is best suited to narrow math or science reasoning tasks where cost is the primary constraint. It is not appropriate for coding agents, content pipelines requiring reliable instruction following, or any workflow needing multi-step tool use. Long-context reliability is also poor given its lcr score of 0.13.
At $0.50 input and $2.15 output per million tokens, pricing is low, but the capability gaps are significant. A regional accessibility penalty applies, reflecting limited enterprise adoption outside its primary market. Most business teams will find stronger alternatives at comparable or lower cost.
Assessed June 6, 2026
Editorial notes
DeepSeek R1 0528 offers low-cost access with reasonable math performance, but its agentic and coding scores are very weak, and a -4 point regional penalty applies given limited enterprise availability.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How DeepSeek: R1 0528 compares
DeepSeek: R1 0528 ranks #211 of 378 AI models we track for overall intelligence, #255 of 315 for coding, #285 of 289 for agentic tasks. Its 164K-token context window is larger than 62% of the models we list. At $0.50 per million input tokens it is cheaper than 35% of comparable models.
About DeepSeek: R1 0528
May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active..
Capabilities
Architecture Detail
| Instruct Type | deepseek-r1 |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does DeepSeek: R1 0528 stack up?
Compare side-by-side with other professional models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.50 | $0.000500 |
| Output | $2.15 | $0.002150 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about DeepSeek: R1 0528
How much does DeepSeek: R1 0528 cost?
DeepSeek: R1 0528 costs $0.50 per million input tokens and $2.15 per million output tokens.
What is the context window of DeepSeek: R1 0528?
DeepSeek: R1 0528 has a context window of 163,840 tokens (164K).
Is DeepSeek: R1 0528 good for coding?
On our coding benchmark index, DeepSeek: R1 0528 ranks #255 of 315 models, placing it in the broader range of the field for code generation and debugging.
What can DeepSeek: R1 0528 do?
DeepSeek: R1 0528 supports tool use and function calling.
Who created DeepSeek: R1 0528?
DeepSeek: R1 0528 is developed by DeepSeek and was released on May 28, 2025.
