# DeepSeek-R1-0528 vs DeepSeek V4.1 Flash

> Side-by-side benchmark comparison for DeepSeek-R1-0528 and DeepSeek V4.1 Flash across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/deepseek-r1-0528-vs-deepseek-v4-1-flash
- Last updated: October 14, 2026

- Shared sourced benchmarks: 3
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: DeepSeek-R1-0528 and DeepSeek V4.1 Flash share only 3 sourced benchmark rows.

## Summary

- Only 3 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- DeepSeek V4.1 Flash has the larger published context window at 1M.

## Model Snapshot

| Property | DeepSeek-R1-0528 | DeepSeek V4.1 Flash |
|----------|----------|----------|
| Creator | DeepSeek | DeepSeek |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 128K | 1M |
| Independent public score (not head-to-head) | null | 64.85 |
| Benchmarks Covered | 10 | 29 |
| Pricing (input/output) | N/A | $0.30 / $1.20 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- DeepSeek-R1-0528 public-lane score: Coming soon
- DeepSeek V4.1 Flash public-lane score: 62 (Supported · #24/124)

| Benchmark | DeepSeek-R1-0528 | DeepSeek V4.1 Flash | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | Coming soon | 90.6% | Coming soon |
| terminalBench3 | Coming soon | 30% | Coming soon |
| Terminal-Bench 4.0 | Coming soon | 31.20% | Coming soon |
| CyberGym | Coming soon | 88.1% | Coming soon |
| ExploitGym | Coming soon | 15.3% | Coming soon |
| HLE w/ tools | Coming soon | 63.9% | Coming soon |
| AutomationBench | Coming soon | 54.8% | Coming soon |
| Agents' Last Exam | Coming soon | 31.8% | Coming soon |
| Terminal-Bench 2.1 (Vals) | Coming soon | 74.5% | Coming soon |
| CWE-bench v1 | Coming soon | 55.0% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- DeepSeek-R1-0528 public-lane score: Coming soon
- DeepSeek V4.1 Flash public-lane score: 60.8 (Supported · #18/148)

| Benchmark | DeepSeek-R1-0528 | DeepSeek V4.1 Flash | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench | 73.3% | Coming soon | Coming soon |
| Codeforces | 1930.0 | 3471.0 | DeepSeek V4.1 Flash |
| SWE-bench Verified | 57.6% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 90.6% | Coming soon |
| terminalBench3 | Coming soon | 30% | Coming soon |
| DeepSWE | Coming soon | 74.2% | Coming soon |
| ProgramBench | Coming soon | 20.3% | Coming soon |
| NL2Repo | Coming soon | 65.4% | Coming soon |
| OpenHarmony Bench | Coming soon | 60.3% | Coming soon |
| Bug Hunt Bench | Coming soon | 21.7 fixes | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- DeepSeek-R1-0528 public-lane score: Coming soon
- DeepSeek V4.1 Flash public-lane score: 83.4 (Unranked · 4 rankable rows)

| Benchmark | DeepSeek-R1-0528 | DeepSeek V4.1 Flash | Winner |
|-----------|-----------|-----------|--------|
| JevBench 1.4 | Coming soon | 4.77 | Coming soon |
| JevBench 1.5 | Coming soon | 6.65 | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- DeepSeek-R1-0528 public-lane score: Coming soon
- DeepSeek V4.1 Flash public-lane score: 77.9 (Unranked · 1 rankable row)

| Benchmark | DeepSeek-R1-0528 | DeepSeek V4.1 Flash | Winner |
|-----------|-----------|-----------|--------|
| Chartography (tools) | Coming soon | 78.9% | Coming soon |
| BabyVision w/ Python | Coming soon | 89.6% | Coming soon |
| ZeroBench w/ Python | Coming soon | 49.0% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- DeepSeek-R1-0528 public-lane score: Coming soon
- DeepSeek V4.1 Flash public-lane score: 65.1 (Supported · #34/181)

| Benchmark | DeepSeek-R1-0528 | DeepSeek V4.1 Flash | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Redux | 93.4% | Coming soon | Coming soon |
| MMLU-Pro | 85% | Coming soon | Coming soon |
| GPQA | 81% | 90.9% | DeepSeek V4.1 Flash |
| SimpleQA | 27.8% | Coming soon | Coming soon |
| HLE | 17.7% | 36.8% | DeepSeek V4.1 Flash |
| GPQA-D | Coming soon | 90.9% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- DeepSeek-R1-0528 public-lane score: Coming soon
- DeepSeek V4.1 Flash public-lane score: 70.1 (Unranked · 3 rankable rows)

| Benchmark | DeepSeek-R1-0528 | DeepSeek V4.1 Flash | Winner |
|-----------|-----------|-----------|--------|
| AIME 2024 | 91.4% | Coming soon | Coming soon |
| AIME 2025 | 87.5% | Coming soon | Coming soon |
| Apex | Coming soon | 65.6% | Coming soon |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 67.368% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 26.829% | Coming soon |

## FAQ

### Is there enough evidence to pick between DeepSeek-R1-0528 and DeepSeek V4.1 Flash?

Not yet. The models share only 3 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [DeepSeek-R1-0528 vs DeepSeek-R1](/compare/deepseek-r1-vs-deepseek-r1-0528)
- [DeepSeek V4.1 Flash vs DeepSeek-R1](/compare/deepseek-r1-vs-deepseek-v4-1-flash)
- [DeepSeek-R1-0528 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-deepseek-r1-0528)
- [DeepSeek V4.1 Flash vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-deepseek-v4-1-flash)

## Explore More

- [DeepSeek-R1-0528 profile](/models/deepseek-r1-0528)
- [DeepSeek V4.1 Flash profile](/models/deepseek-v4-1-flash)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)