DeepSeek V4 Pro 0423 vs GPT-5 Mini
DeepSeek V4 Pro 0423 leads GPT-5 Mini on coding, 38.7 to 34.2 on the Vibe Coding Index, and GPT-5 Mini costs 1.5x less per output token ($2.00 vs $2.976 per million). Updated October 22, 2026; 62 benchmarks have a result for both.
DeepSeek V4 Pro 0423 or GPT-5 Mini: which to pick
Pick DeepSeek V4 Pro 0423 for coding: it scores 38.7 on the Vibe Coding Index against 34.2 for GPT-5 Mini.
Pick GPT-5 Mini for output tokens 1.5x cheaper ($2.00 vs $2.976 per million) and a lower cost per solved task ($0.08 against $0.57).
- Shared results
- 62
- DeepSeek V4 Pro 0423 only
- 22
- GPT-5 Mini only
- 39
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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, six public coding benchmarks
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 scores 38.7 against 34.2.
5 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 30.4 against 20.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Pro 0423 has a AA Agentic Index result, 26.3.
Directional only
Reasoning
GPQA Diamond
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 89.4% against 80.3%.
Same board, both measured
Math
AIME
No call
Only GPT-5 Mini has a AIME result, 91.5%.
Directional only
Knowledge
MMLU Pro
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 87.3% against 82.2%.
Same board, both measured
Web design
Design Arena: websites
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 1234 against 1125.
Same board, both measured
Long documents
Listed context window
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 takes 1.05M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5 Mini
DeepSeek V4 Pro 0423 $0.0028, GPT-5 Mini $0.0013 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5 Mini
DeepSeek V4 Pro 0423 $0.57, GPT-5 Mini $0.08.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V4 Pro 0423 38.7 from 5 benchmarks, GPT-5 Mini 34.2 from 2 benchmarks.
- Widest category
- Agentic work, 20.5 points apart on average over 1 shared benchmark.
- Widest single gap
- Vibe Code Bench (Vals AI): DeepSeek V4 Pro 0423 49.9% against GPT-5 Mini 14.2%, 35.8 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Pro 0423 $2.976 against GPT-5 Mini $2.00 per million output tokens, 1.5x apart.
- Context window
- DeepSeek V4 Pro 0423 takes 1.05M tokens, GPT-5 Mini 400K.
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 0423 | Bars | GPT-5 Mini | Ties |
|---|---|---|---|---|
| Coding | 5 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 6 | 2 | ||
| Math | 4 | 2 | ||
| Knowledge | 7 | 4 | ||
| Web design | 8 | 0 | ||
| General | 19 | 1 | ||
| All shared boards | 52 | 10 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index51
| Benchmark | DeepSeek V4 Pro 0423 | GPT-5 Mini | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 59.8% | Only GPT-5 Mini measured |
| SWE-bench Multilingual | Not measured | 39.7% | Only GPT-5 Mini measured |
| LMArena WebDev | 1447 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| AA Coding Index | 59.4 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LiveCodeBench (Vals AI) | 87.5% | 86.6% | DeepSeek V4 Pro 0423 |
| SWE-bench Verified (Vals AI) | 77.4% | 60.8% | DeepSeek V4 Pro 0423 |
| Terminal-Bench 4 (Vals AI) | 11.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Vibe Code Bench (Vals AI) | 49.9% | 14.2% | DeepSeek V4 Pro 0423 |
| Code migration (Vals AI) | 26.2% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Terminal-Bench 2.1 (Vals AI) | 50.2% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SkillsBench (Vals AI) | 51.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 83.8% | Only GPT-5 Mini measured |
| SciCode | Not measured | 39.0% | Only GPT-5 Mini measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 33.3% | Only GPT-5 Mini measured |
| Terminal-Bench | Not measured | 34.8% | Only GPT-5 Mini measured |
| FrontierCode | 17.6% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| WeirdML | 48.9% | 52.7% | GPT-5 Mini |
| ALE-Bench | 1006.1 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: coding | 1470 | 1406 | DeepSeek V4 Pro 0423 |
| LMArena Text: software and IT | 1469 | 1394 | DeepSeek V4 Pro 0423 |
| LMArena WebDev: React | 1441 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena WebDev: HTML | 1435 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V4 Pro 0423 | GPT-5 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.4 | 20.6 | DeepSeek V4 Pro 0423 |
| Epoch Capabilities Index | 149.1 | 145.3 | DeepSeek V4 Pro 0423 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4 Pro 0423 | GPT-5 Mini | Leader |
|---|---|---|---|
| AA Agentic Index | 26.3 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building web apps | 1000 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building full-stack apps | 948 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building Godot games | 1059 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Finance Agent (Vals AI) | 44.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Tax Agent Bench (Vals AI) | 25.2% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Legal Research Bench (Vals AI) | 23.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Excel Modeling Benchmark (Vals AI) | 51.6% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| τ²-Bench Telecom | Not measured | 71.1% | Only GPT-5 Mini measured |
| Vending-Bench 2 | $3,285 | -$31 | DeepSeek V4 Pro 0423 |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 55.5% | Only GPT-5 Mini measured |
| Neither model has a result on the other 30 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index62
| Benchmark | DeepSeek V4 Pro 0423 | GPT-5 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | 89.4% | 80.3% | DeepSeek V4 Pro 0423 |
| MMMU Pro (Vals AI) | Not measured | 78.9% | Only GPT-5 Mini measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 82.8% | Only GPT-5 Mini measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 21.5% | Only GPT-5 Mini measured |
| GPQA Diamond (Epoch AI run) | 90.9% | 75.0% | DeepSeek V4 Pro 0423 |
| ARC-AGI | Not measured | 54.3% | Only GPT-5 Mini measured |
| ARC-AGI-2 | Not measured | 4.4% | Only GPT-5 Mini measured |
| Chess puzzles | 19.0% | 24.0% | GPT-5 Mini |
| Mystery game puzzles | 17.0% | 10.0% | DeepSeek V4 Pro 0423 |
| VPCT | Not measured | 40.2% | Only GPT-5 Mini measured |
| LMArena Text: hard prompts | 1461 | 1380 | DeepSeek V4 Pro 0423 |
| LMArena Text: expert | 1463 | 1379 | DeepSeek V4 Pro 0423 |
| LMArena Text: hard prompts in English | 1466 | 1383 | DeepSeek V4 Pro 0423 |
| LMArena Vision: diagrams | Not measured | 1202 | Only GPT-5 Mini measured |
| LMArena Vision: homework | Not measured | 1210 | Only GPT-5 Mini measured |
| Kagi LLM Benchmark | 53.5% | 70.3% | GPT-5 Mini |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index42
| Benchmark | DeepSeek V4 Pro 0423 | GPT-5 Mini | Leader |
|---|---|---|---|
| AIME | Not measured | 91.5% | Only GPT-5 Mini measured |
| MATH 500 (Vals AI) | Not measured | 94.8% | Only GPT-5 Mini measured |
| MGSM (Vals AI) | Not measured | 92.6% | Only GPT-5 Mini measured |
| AA Math Index | Not measured | 90.7 | Only GPT-5 Mini measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 90.7% | Only GPT-5 Mini measured |
| OTIS Mock AIME | 96.7% | 86.7% | DeepSeek V4 Pro 0423 |
| FrontierMath, tiers 1 to 3 | 45.3% | 46.7% | GPT-5 Mini |
| FrontierMath, tier 4 | 2.4% | 12.2% | GPT-5 Mini |
| ProofBench | 16.0% | 9.0% | DeepSeek V4 Pro 0423 |
| MATH level 5 | Not measured | 97.8% | Only GPT-5 Mini measured |
| LMArena Text: math | 1443 | 1378 | DeepSeek V4 Pro 0423 |
| LMArena Text: mathematical work | 1455 | 1380 | DeepSeek V4 Pro 0423 |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index74
| Benchmark | DeepSeek V4 Pro 0423 | GPT-5 Mini | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | 82.2% | DeepSeek V4 Pro 0423 |
| LegalBench (Vals AI) | 80.3% | 81.8% | GPT-5 Mini |
| CaseLaw (Vals AI) | 59.4% | 68.5% | GPT-5 Mini |
| CorpFin (Vals AI) | 61.4% | 60.2% | DeepSeek V4 Pro 0423 |
| TaxEval (Vals AI) | 72.1% | 75.2% | GPT-5 Mini |
| MortgageTax (Vals AI) | Not measured | 66.9% | Only GPT-5 Mini measured |
| MedQA (Vals AI) | Not measured | 96.1% | Only GPT-5 Mini measured |
| MedCode (Vals AI) | 40.5% | 43.0% | GPT-5 Mini |
| MMLU Pro (Artificial Analysis run) | Not measured | 83.7% | Only GPT-5 Mini measured |
| SimpleQA Verified | 47.0% | 21.6% | DeepSeek V4 Pro 0423 |
| LMArena Text: science | 1470 | 1371 | DeepSeek V4 Pro 0423 |
| LMArena Text: medicine and healthcare | 1466 | 1380 | DeepSeek V4 Pro 0423 |
| LMArena Text: legal and government | 1464 | 1375 | DeepSeek V4 Pro 0423 |
| LMArena Text: business and finance | 1443 | 1358 | DeepSeek V4 Pro 0423 |
| FACTS Benchmark Suite | Not measured | 38.6% | Only GPT-5 Mini measured |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | DeepSeek V4 Pro 0423 | GPT-5 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1234 | 1125 | DeepSeek V4 Pro 0423 |
| Design Arena: UI components | 1219 | 1103 | DeepSeek V4 Pro 0423 |
| Design Arena: game dev | 1228 | 1129 | DeepSeek V4 Pro 0423 |
| Design Arena: data viz | 1203 | 1131 | DeepSeek V4 Pro 0423 |
| Design Arena: 3D | 1253 | 1036 | DeepSeek V4 Pro 0423 |
| Design Arena: all code categories | 1240 | 1114 | DeepSeek V4 Pro 0423 |
| Design Arena: SVG | 1139 | 1091 | DeepSeek V4 Pro 0423 |
| Design Arena: ASCII art | 1149 | 1125 | DeepSeek V4 Pro 0423 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index191
| Benchmark | DeepSeek V4 Pro 0423 | GPT-5 Mini | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 62.9% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SAGE (Vals AI) | Not measured | 43.0% | Only GPT-5 Mini measured |
| MedScribe (Vals AI) | 75.1% | 80.6% | GPT-5 Mini |
| IFBench | Not measured | 75.4% | Only GPT-5 Mini measured |
| Long context reasoning (AA-LCR) | Not measured | 72.3% | Only GPT-5 Mini measured |
| DTBench | 90.7% | 80.5% | DeepSeek V4 Pro 0423 |
| LMCA | 41.2% | 34.2% | DeepSeek V4 Pro 0423 |
| Fiction.LiveBench | Not measured | 69.4% | Only GPT-5 Mini measured |
| Creative writing (Lech Mazur) | Not measured | 83.1% | Only GPT-5 Mini measured |
| Surface Evolver Bench | 40.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| CL-bench Life | 13.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text | 1451 | 1373 | DeepSeek V4 Pro 0423 |
| LMArena Text: instruction following | 1445 | 1357 | DeepSeek V4 Pro 0423 |
| LMArena Text: creative writing | 1446 | 1325 | DeepSeek V4 Pro 0423 |
| LMArena Vision | Not measured | 1202 | Only GPT-5 Mini measured |
| LMArena Text: English | 1459 | 1379 | DeepSeek V4 Pro 0423 |
| LMArena Text: non-English | 1439 | 1363 | DeepSeek V4 Pro 0423 |
| LMArena Text: Chinese | 1481 | 1386 | DeepSeek V4 Pro 0423 |
| LMArena Text: German | 1458 | 1366 | DeepSeek V4 Pro 0423 |
| LMArena Text: Japanese | 1446 | 1341 | DeepSeek V4 Pro 0423 |
| LMArena Text: Korean | 1409 | 1308 | DeepSeek V4 Pro 0423 |
| LMArena Text: French | 1473 | 1386 | DeepSeek V4 Pro 0423 |
| LMArena Text: Spanish | 1457 | 1354 | DeepSeek V4 Pro 0423 |
| LMArena Text: Russian | 1453 | 1362 | DeepSeek V4 Pro 0423 |
| LMArena Text: Polish | 1461 | 1378 | DeepSeek V4 Pro 0423 |
| LMArena Text: multi-turn | 1468 | 1363 | DeepSeek V4 Pro 0423 |
| LMArena Text: longer queries | 1458 | 1355 | DeepSeek V4 Pro 0423 |
| LMArena Text: writing and language | 1447 | 1344 | DeepSeek V4 Pro 0423 |
| LMArena Text: entertainment and media | 1431 | 1340 | DeepSeek V4 Pro 0423 |
| LMArena Vision: English | Not measured | 1216 | Only GPT-5 Mini measured |
| LMArena Vision: Chinese | Not measured | 1214 | Only GPT-5 Mini measured |
| LMArena Vision: reading text | Not measured | 1199 | Only GPT-5 Mini measured |
| LMArena Vision: humor | Not measured | 1205 | Only GPT-5 Mini measured |
| LMArena Vision: captioning | Not measured | 1217 | Only GPT-5 Mini measured |
| LMArena Vision: recognizing things | Not measured | 1226 | Only GPT-5 Mini measured |
| LMArena Vision: creative writing | Not measured | 1181 | Only GPT-5 Mini measured |
| Neither model has a result on the other 10 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Pro 0423 | GPT-5 Mini | 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
GPT-5 Mini costs less
Repository review
50K input + 3K output tokens
GPT-5 Mini costs less
Agent loop
200K input + 10K output tokens
GPT-5 Mini 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 0423 | OpenAI GPT-5 Mini |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | April 24, 2026 | August 7, 2025 |
| Context window | 1.05M | 400K |
| Input $/Mtok | $1.358 | $0.25 |
| Output $/Mtok | $2.976 | $2.00 |
| Coding index | 38.7 | 34.2 |
| Independent measurements behind it | 5 | 2 |
| Cost per solved task | $0.57 | $0.08 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Pro 0423 better than GPT-5 Mini for coding?
Pick DeepSeek V4 Pro 0423 for coding: it scores 38.7 on the Vibe Coding Index against 34.2 for GPT-5 Mini. Pick GPT-5 Mini for output tokens 1.5x cheaper ($2.00 vs $2.976 per million) and a lower cost per solved task ($0.08 against $0.57).
Which is cheaper, DeepSeek V4 Pro 0423 or GPT-5 Mini?
DeepSeek V4 Pro 0423 costs $1.358 per million input tokens and $2.976 per million output tokens; GPT-5 Mini costs $0.25 and $2.00. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0423 costs $0.57 and GPT-5 Mini $0.08.
Which has the bigger context window, DeepSeek V4 Pro 0423 or GPT-5 Mini?
DeepSeek V4 Pro 0423, with 1.05M tokens against 400K.
How many benchmarks is the DeepSeek V4 Pro 0423 vs GPT-5 Mini comparison based on?
62 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Pro 0423's coding index rests on 5 independent benchmarks and GPT-5 Mini's on 2. Where only one model has a result, the page says so instead of naming a winner.