DeepSeek V4 Pro 0813 vs Step 5 Preview
Updated October 21, 2026. 42 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Step 5 Preview for coding: it scores 71.4 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813.
Pick DeepSeek V4 Pro 0813 when output tokens cost 1.4x less, or when what matters is LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.
- Shared results
- 42
- DeepSeek V4 Pro 0813 only
- 36
- Step 5 Preview only
- 19
- Like-for-like categories
- 7 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
Step 5 Preview
Step 5 Preview scores 71.4 against 54.6.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Step 5 Preview
Step 5 Preview leads, 43.7 against 36.0.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Pro 0813 has a AA Agentic Index result, 41.3.
Directional only
Reasoning
GPQA Diamond
No call
Only DeepSeek V4 Pro 0813 has a GPQA Diamond result, 92.4%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V4 Pro 0813 has a MMLU Pro result, 87.0%.
Directional only
General
Vals Index
No call
Only DeepSeek V4 Pro 0813 has a Vals Index result, 53.0%.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 $0.0016, Step 5 Preview $0.0024 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only DeepSeek V4 Pro 0813 has the number, $0.10.
Directional only
At a glance
- Coding index
- DeepSeek V4 Pro 0813 54.6 from 1 benchmark, Step 5 Preview 71.4 from 2 benchmarks.
- Widest category
- Intelligence, 7.7 points apart on average over 1 shared benchmark.
- Widest single gap
- Terminal-Bench 4 (Vals AI): DeepSeek V4 Pro 0813 14.1% against Step 5 Preview 31.8%, 17.7 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Pro 0813 $1.98 against Step 5 Preview $2.70 per million output tokens, 1.4x apart.
- Context window
- Both take 1.05M tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | DeepSeek V4 Pro 0813 | Bars | Step 5 Preview | Ties |
|---|---|---|---|---|
| Coding | 6 | 4 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 3 | 3 | ||
| Reasoning | 1 | 3 | ||
| Math | 1 | 2 | ||
| Knowledge | 4 | 0 | ||
| General | 11 | 3 | ||
| All shared boards | 26 | 16 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index64
| Benchmark | DeepSeek V4 Pro 0813 | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 85.6% | Only Step 5 Preview measured |
| LMArena WebDev | 1582 | 1567 | DeepSeek V4 Pro 0813 |
| AA Coding Index | 68.8 | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LiveCodeBench (Vals AI) | 87.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SWE-bench Verified (Vals AI) | 96.4% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Terminal-Bench 4 (Vals AI) | 14.1% | 31.8% | Step 5 Preview |
| Vibe Code Bench (Vals AI) | 82.3% | 70.4% | DeepSeek V4 Pro 0813 |
| Code migration (Vals AI) | 41.5% | 39.0% | DeepSeek V4 Pro 0813 |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| IOI (Vals AI) | 51.6% | 38.1% | DeepSeek V4 Pro 0813 |
| Terminal-Bench 2.1 (Vals AI) | 54.7% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 40.8% | Only Step 5 Preview measured |
| Vibe Code Bench 1-100 (Vals AI) | 17.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SkillsBench (Vals AI) | 53.8% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| CyberBench (Vals AI) | 72.9% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SciCode | 51.0% | 58.9% | Step 5 Preview |
| FrontierCode | 28.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| WeirdML | 66.2% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| ALE-Bench | 1403.2 | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMArena Text: coding | 1469 | 1485 | Step 5 Preview |
| LMArena Text: software and IT | 1462 | 1473 | Step 5 Preview |
| LMArena WebDev: React | 1588 | 1583 | DeepSeek V4 Pro 0813 |
| LMArena WebDev: HTML | 1566 | 1556 | DeepSeek V4 Pro 0813 |
| LMArena WebDev: from an image | Not measured | 1550 | Only Step 5 Preview measured |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V4 Pro 0813 | Step 5 Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 36.0 | 43.7 | Step 5 Preview |
| Epoch Capabilities Index | 155.6 | Not measured | Only DeepSeek V4 Pro 0813 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | DeepSeek V4 Pro 0813 | Step 5 Preview | Leader |
|---|---|---|---|
| AA Agentic Index | 41.3 | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LiveBench research | Not measured | 72.8% | Only Step 5 Preview measured |
| LiveBench browser | Not measured | 24.0% | Only Step 5 Preview measured |
| LiveBench long agentic | Not measured | 27.5% | Only Step 5 Preview measured |
| SREBench (Vals AI) | 1.9% | 0.4% | DeepSeek V4 Pro 0813 |
| Finance Agent (Vals AI) | 50.4% | 50.7% | Step 5 Preview |
| Tax Agent Bench (Vals AI) | 26.8% | 27.3% | Step 5 Preview |
| Legal Research Bench (Vals AI) | 40.9% | 40.4% | DeepSeek V4 Pro 0813 |
| Harvey's Legal Agent Benchmark (Vals AI) | 10.8% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Excel Modeling Benchmark (Vals AI) | 52.8% | 57.1% | Step 5 Preview |
| BioMysteryBench (Vals AI) | Not measured | 67.4% | Only Step 5 Preview measured |
| Terminal-Bench-Science (Vals AI) | 4.3% | 2.9% | DeepSeek V4 Pro 0813 |
| Vals Science Index | Not measured | 29.6% | Only Step 5 Preview measured |
| APEX-Agents | 47.3% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Neither model has a result on the other 25 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | DeepSeek V4 Pro 0813 | Step 5 Preview | Leader |
|---|---|---|---|
| GPQA Diamond | 92.4% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LiveBench reasoning | Not measured | 83.8% | Only Step 5 Preview measured |
| MysteryMechanism (Vals AI) | Not measured | 18.5% | Only Step 5 Preview measured |
| GPQA Diamond (Artificial Analysis run) | 92.8% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Humanity's Last Exam (Artificial Analysis run) | 41.0% | 46.5% | Step 5 Preview |
| GPQA Diamond (Epoch AI run) | 91.7% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| ARC-AGI | 90.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| ARC-AGI-2 | 61.3% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Chess puzzles | 46.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Mystery game puzzles | 43.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMArena Text: hard prompts | 1458 | 1461 | Step 5 Preview |
| LMArena Text: expert | 1459 | 1485 | Step 5 Preview |
| LMArena Text: hard prompts in English | 1463 | 1454 | DeepSeek V4 Pro 0813 |
| LMArena Vision: diagrams | Not measured | 1308 | Only Step 5 Preview measured |
| LMArena Vision: homework | Not measured | 1265 | Only Step 5 Preview measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | DeepSeek V4 Pro 0813 | Step 5 Preview | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.6% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| FrontierMath, tiers 1 to 3 | 64.6% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| FrontierMath, tier 4 | 26.8% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| ProofBench | 50.0% | 42.0% | DeepSeek V4 Pro 0813 |
| LMArena Text: math | 1441 | 1458 | Step 5 Preview |
| LMArena Text: mathematical work | 1443 | 1460 | Step 5 Preview |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | DeepSeek V4 Pro 0813 | Step 5 Preview | Leader |
|---|---|---|---|
| MMLU Pro | 87.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LegalBench (Vals AI) | 82.4% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| CorpFin (Vals AI) | 65.4% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| TaxEval (Vals AI) | 73.1% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| MedCode (Vals AI) | 42.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SimpleQA Verified | 52.9% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMArena Text: science | 1457 | 1454 | DeepSeek V4 Pro 0813 |
| LMArena Text: medicine and healthcare | 1446 | 1439 | DeepSeek V4 Pro 0813 |
| LMArena Text: legal and government | 1459 | 1437 | DeepSeek V4 Pro 0813 |
| LMArena Text: business and finance | 1442 | 1435 | DeepSeek V4 Pro 0813 |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | DeepSeek V4 Pro 0813 | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench design | Not measured | 76.9% | Only Step 5 Preview measured |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index113
| Benchmark | DeepSeek V4 Pro 0813 | Step 5 Preview | Leader |
|---|---|---|---|
| Vals Index | 53.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LiveBench data analysis | Not measured | 63.5% | Only Step 5 Preview measured |
| Public Benefits Bench (Vals AI) | Not measured | 58.1% | Only Step 5 Preview measured |
| MedScribe (Vals AI) | 80.2% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Long context reasoning (AA-LCR) | 80.3% | 88.3% | Step 5 Preview |
| DTBench | 93.9% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMCA | 45.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMArena Text | 1446 | 1440 | DeepSeek V4 Pro 0813 |
| LMArena Text: instruction following | 1448 | 1438 | DeepSeek V4 Pro 0813 |
| LMArena Text: creative writing | 1439 | 1409 | DeepSeek V4 Pro 0813 |
| LMArena Vision | Not measured | 1265 | Only Step 5 Preview measured |
| LMArena Text: English | 1457 | 1447 | DeepSeek V4 Pro 0813 |
| LMArena Text: non-English | 1431 | 1428 | DeepSeek V4 Pro 0813 |
| LMArena Text: Chinese | 1481 | 1500 | Step 5 Preview |
| LMArena Text: Japanese | Not measured | 1383 | Only Step 5 Preview measured |
| LMArena Text: Korean | 1449 | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMArena Text: French | 1446 | 1438 | DeepSeek V4 Pro 0813 |
| LMArena Text: Spanish | 1435 | 1441 | Step 5 Preview |
| LMArena Text: Russian | 1448 | 1433 | DeepSeek V4 Pro 0813 |
| LMArena Text: multi-turn | 1454 | 1437 | DeepSeek V4 Pro 0813 |
| LMArena Text: longer queries | 1458 | 1449 | DeepSeek V4 Pro 0813 |
| LMArena Text: writing and language | 1443 | 1425 | DeepSeek V4 Pro 0813 |
| LMArena Text: entertainment and media | 1424 | 1412 | DeepSeek V4 Pro 0813 |
| LMArena Vision: English | Not measured | 1290 | Only Step 5 Preview measured |
| LMArena Vision: reading text | Not measured | 1282 | Only Step 5 Preview measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Pro 0813 | Step 5 Preview | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
DeepSeek V4 Pro 0813 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Pro 0813 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Pro 0813 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | DeepSeek V4 Pro 0813 | StepFun Step 5 Preview |
|---|---|---|
| Maker | DeepSeek | StepFun |
| Weights | Open weights | Open weights |
| Released | August 12, 2026 | October 8, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.66 | $1.00 |
| Output $/Mtok | $1.98 | $2.70 |
| Coding index | 54.6 | 71.4 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | $0.10 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Pro 0813 better than Step 5 Preview for coding?
Pick Step 5 Preview for coding: it scores 71.4 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813. Pick DeepSeek V4 Pro 0813 when output tokens cost 1.4x less, or when what matters is LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.
Which is cheaper, DeepSeek V4 Pro 0813 or Step 5 Preview?
DeepSeek V4 Pro 0813 costs $0.66 per million input tokens and $1.98 per million output tokens; Step 5 Preview costs $1.00 and $2.70. Cost per solved task is known for DeepSeek V4 Pro 0813 only.
Which has the bigger context window, DeepSeek V4 Pro 0813 or Step 5 Preview?
Neither: both take 1.05M tokens.
How many benchmarks is the DeepSeek V4 Pro 0813 vs Step 5 Preview comparison based on?
42 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0813's coding index rests on 1 independent benchmark and Step 5 Preview's on 2. Where only one model has a result, the page says so instead of naming a winner.