Model card
DeepSeek-R1-0528.
DeepSeekopen-source
§ 01 · Benchmarks
Every benchmark DeepSeek-R1-0528 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | LiveCodeBench | Computer Code · Code Generation | pass@1 | 73.3% | #6 | — | source ↗ |
| 02 | PLCC | Natural Language Processing · Polish Cultural Competency | history | 91.0% | #11 | — | source ↗ |
| 03 | MMLU-Pro | Reasoning · Commonsense Reasoning | accuracy | 85.0% | #17 | 2026-04-20 | source ↗ |
| 04 | SWE-Bench Verified | Computer Code · Code Generation | resolve-rate | 57.6% | #29 | — | source ↗ |
| 05 | PLCC | Natural Language Processing · Polish Cultural Competency | grammar | 73.0% | #39 | — | source ↗ |
| 06 | PLCC | Natural Language Processing · Polish Cultural Competency | geography | 85.0% | #41 | — | source ↗ |
| 07 | PLCC | Natural Language Processing · Polish Cultural Competency | average | 76.2% | #44 | — | source ↗ |
| 08 | PLCC | Natural Language Processing · Polish Cultural Competency | vocabulary | 68.0% | #48 | — | source ↗ |
| 09 | PLCC | Natural Language Processing · Polish Cultural Competency | art-and-entertainment | 65.0% | #49 | — | source ↗ |
| 10 | PLCC | Natural Language Processing · Polish Cultural Competency | culture-and-tradition | 75.0% | #53 | — | source ↗ |
| 11 | SWE-bench Verified | Agentic AI · SWE-bench | resolve-rate | 44.6% | #69 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where DeepSeek-R1-0528 actually performs.
§ 04 · Related models
Other DeepSeek models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
sdadas/PLCC
7
results
deepseek-model-card
1
result
llm-stats
1
result
deepseek-blog
1
result
editorial
1
result
9 of 11 rows marked verified.