DeepSeek V4 Pro 0423 vs GPT-6.1 Sol
GPT-6.1 Sol leads DeepSeek V4 Pro 0423 on coding, 82.4 to 38.7 on the Vibe Coding Index, and DeepSeek V4 Pro 0423 costs 3.7x less per output token ($2.716 vs $10.00 per million). Updated October 21, 2026; 59 benchmarks have a result for both.
DeepSeek V4 Pro 0423 or GPT-6.1 Sol: which to pick
Pick GPT-6.1 Sol for coding: it scores 82.4 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423.
Pick DeepSeek V4 Pro 0423 for output tokens 3.7x cheaper ($2.716 vs $10.00 per million) and work measured by Tax Agent Bench (Vals AI) or LMArena Text: hard prompts in English, where it leads.
- Shared results
- 59
- DeepSeek V4 Pro 0423 only
- 25
- GPT-6.1 Sol 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
GPT-6.1 Sol
GPT-6.1 Sol scores 82.4 against 38.7.
5 benchmarks behind each score
Intelligence
AA Intelligence Index
GPT-6.1 Sol
GPT-6.1 Sol leads, 51.8 against 30.4.
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
No call
Only DeepSeek V4 Pro 0423 has a GPQA Diamond result, 89.4%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V4 Pro 0423 has a MMLU Pro result, 87.3%.
Directional only
Web design
Design Arena: websites
GPT-6.1 Sol
GPT-6.1 Sol leads, 1321 against 1234.
Same board, both measured
General
Vals Index
No call
Only GPT-6.1 Sol has a Vals Index result, 63.9%.
Directional only
Long documents
Listed context window
GPT-6.1 Sol
GPT-6.1 Sol takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 $0.0026, GPT-6.1 Sol $0.0070 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only DeepSeek V4 Pro 0423 has the number, $0.57.
Directional only
At a glance
- Coding index
- DeepSeek V4 Pro 0423 38.7 from 5 benchmarks, GPT-6.1 Sol 82.4 from 5 benchmarks.
- Widest category
- Math, 41.6 points apart on average over 6 shared benchmarks.
- Widest single gap
- FrontierMath, tier 4: DeepSeek V4 Pro 0423 2.4% against GPT-6.1 Sol 100.0%, 97.6 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Pro 0423 $2.716 against GPT-6.1 Sol $10.00 per million output tokens, 3.7x apart.
- Context window
- DeepSeek V4 Pro 0423 takes 1.05M tokens, GPT-6.1 Sol 1.05M.
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-6.1 Sol | Ties |
|---|---|---|---|---|
| Coding | 0 | 11 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 1 | 4 | ||
| Reasoning | 1 | 5 | ||
| Math | 0 | 6 | ||
| Knowledge | 2 | 4 | ||
| Web design | 0 | 6 | ||
| General | 10 | 7 | ||
| All shared boards | 14 | 45 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index011
| Benchmark | DeepSeek V4 Pro 0423 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 96.0% | Only GPT-6.1 Sol measured |
| LMArena WebDev | 1447 | 1753 | GPT-6.1 Sol |
| AA Coding Index | 59.4 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LiveCodeBench (Vals AI) | 87.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SWE-bench Verified (Vals AI) | 77.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Terminal-Bench 4 (Vals AI) | 11.1% | 55.0% | GPT-6.1 Sol |
| Vibe Code Bench (Vals AI) | 49.9% | 88.9% | GPT-6.1 Sol |
| Code migration (Vals AI) | 26.2% | 65.1% | GPT-6.1 Sol |
| ProgramBench (Vals AI) | 0.0% | 3.0% | GPT-6.1 Sol |
| IOI (Vals AI) | Not measured | 96.9% | Only GPT-6.1 Sol measured |
| Terminal-Bench 2.1 (Vals AI) | 50.2% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 43.5% | Only GPT-6.1 Sol measured |
| SkillsBench (Vals AI) | 51.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| CyberBench (Vals AI) | Not measured | 39.3% | Only GPT-6.1 Sol measured |
| SciCode | Not measured | 55.8% | Only GPT-6.1 Sol measured |
| FrontierCode | 17.6% | 50.2% | GPT-6.1 Sol |
| WeirdML | 48.9% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| ALE-Bench | 1006.1 | 2743.8 | GPT-6.1 Sol |
| LMArena Text: coding | 1470 | 1478 | GPT-6.1 Sol |
| LMArena Text: software and IT | 1469 | 1476 | GPT-6.1 Sol |
| LMArena WebDev: React | 1441 | 1754 | GPT-6.1 Sol |
| LMArena WebDev: HTML | 1435 | 1800 | GPT-6.1 Sol |
| LMArena WebDev: from an image | Not measured | 1702 | Only GPT-6.1 Sol measured |
| SciCode | Not measured | 9.2% | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 15 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V4 Pro 0423 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.4 | 51.8 | GPT-6.1 Sol |
| Epoch Capabilities Index | 149.1 | 168.4 | GPT-6.1 Sol |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index14
| Benchmark | DeepSeek V4 Pro 0423 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| AA Agentic Index | 26.3 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building web apps | 1000 | 1306 | GPT-6.1 Sol |
| Design Arena: agents building full-stack apps | 948 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building mobile apps | Not measured | 1204 | Only GPT-6.1 Sol measured |
| Design Arena: agents building Godot games | 1059 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: spreadsheets | Not measured | 1242 | Only GPT-6.1 Sol measured |
| LiveBench research | Not measured | 83.5% | Only GPT-6.1 Sol measured |
| LiveBench browser | Not measured | 88.0% | Only GPT-6.1 Sol measured |
| LiveBench long agentic | Not measured | 73.0% | Only GPT-6.1 Sol measured |
| SREBench (Vals AI) | Not measured | 50.8% | Only GPT-6.1 Sol measured |
| Finance Agent (Vals AI) | 44.1% | 52.0% | GPT-6.1 Sol |
| Tax Agent Bench (Vals AI) | 25.2% | 21.8% | DeepSeek V4 Pro 0423 |
| Legal Research Bench (Vals AI) | 23.1% | 38.5% | GPT-6.1 Sol |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 6.3% | Only GPT-6.1 Sol measured |
| Excel Modeling Benchmark (Vals AI) | 51.6% | 70.8% | GPT-6.1 Sol |
| BioMysteryBench (Vals AI) | Not measured | 79.6% | Only GPT-6.1 Sol measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 52.9% | Only GPT-6.1 Sol measured |
| Vals Science Index | Not measured | 59.6% | Only GPT-6.1 Sol measured |
| Robo-bench (Vals AI) | Not measured | 28.3% | Only GPT-6.1 Sol measured |
| APEX-Agents | Not measured | 60.0% | Only GPT-6.1 Sol measured |
| SpireClimb | Not measured | 24.7% | Only GPT-6.1 Sol measured |
| Vending-Bench 2 | $3,285 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Neither model has a result on the other 19 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | DeepSeek V4 Pro 0423 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| GPQA Diamond | 89.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LiveBench reasoning | Not measured | 92.6% | Only GPT-6.1 Sol measured |
| MysteryMechanism (Vals AI) | Not measured | 46.4% | Only GPT-6.1 Sol measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 52.9% | Only GPT-6.1 Sol measured |
| GPQA Diamond (Epoch AI run) | 90.9% | 95.4% | GPT-6.1 Sol |
| ARC-AGI | Not measured | 98.5% | Only GPT-6.1 Sol measured |
| ARC-AGI-2 | Not measured | 94.2% | Only GPT-6.1 Sol measured |
| Chess puzzles | 19.0% | 68.0% | GPT-6.1 Sol |
| Mystery game puzzles | 17.0% | 80.0% | GPT-6.1 Sol |
| EBR-bench | Not measured | 54.3% | Only GPT-6.1 Sol measured |
| LMArena Text: hard prompts | 1461 | 1463 | GPT-6.1 Sol |
| LMArena Text: expert | 1463 | 1489 | GPT-6.1 Sol |
| LMArena Text: hard prompts in English | 1466 | 1465 | DeepSeek V4 Pro 0423 |
| LMArena Vision: diagrams | Not measured | 1306 | Only GPT-6.1 Sol measured |
| LMArena Vision: homework | Not measured | 1356 | Only GPT-6.1 Sol measured |
| Kagi LLM Benchmark | 53.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | DeepSeek V4 Pro 0423 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| OTIS Mock AIME | 96.7% | 100.0% | GPT-6.1 Sol |
| FrontierMath, tiers 1 to 3 | 45.3% | 93.7% | GPT-6.1 Sol |
| FrontierMath, tier 4 | 2.4% | 100.0% | GPT-6.1 Sol |
| ProofBench | 16.0% | 99.0% | GPT-6.1 Sol |
| LMArena Text: math | 1443 | 1489 | GPT-6.1 Sol |
| LMArena Text: mathematical work | 1455 | 1513 | GPT-6.1 Sol |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index24
| Benchmark | DeepSeek V4 Pro 0423 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LegalBench (Vals AI) | 80.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| CaseLaw (Vals AI) | 59.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| CorpFin (Vals AI) | 61.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| TaxEval (Vals AI) | 72.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| MedCode (Vals AI) | 40.5% | 48.8% | GPT-6.1 Sol |
| SimpleQA Verified | 47.0% | 73.9% | GPT-6.1 Sol |
| LMArena Text: science | 1470 | 1444 | DeepSeek V4 Pro 0423 |
| LMArena Text: medicine and healthcare | 1466 | 1433 | DeepSeek V4 Pro 0423 |
| LMArena Text: legal and government | 1464 | 1471 | GPT-6.1 Sol |
| LMArena Text: business and finance | 1443 | 1445 | GPT-6.1 Sol |
| FACTS Benchmark Suite | Not measured | 75.3% | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | DeepSeek V4 Pro 0423 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| Design Arena: websites | 1234 | 1321 | GPT-6.1 Sol |
| Design Arena: UI components | 1222 | 1330 | GPT-6.1 Sol |
| Design Arena: game dev | 1229 | 1389 | GPT-6.1 Sol |
| Design Arena: data viz | 1203 | 1280 | GPT-6.1 Sol |
| Design Arena: 3D | 1254 | 1463 | GPT-6.1 Sol |
| Design Arena: all code categories | 1240 | 1346 | GPT-6.1 Sol |
| Design Arena: SVG | 1140 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: ASCII art | 1149 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LiveBench design | Not measured | 82.1% | Only GPT-6.1 Sol measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index107
| Benchmark | DeepSeek V4 Pro 0423 | GPT-6.1 Sol | Leader |
|---|---|---|---|
| Vals Index | Not measured | 63.9% | Only GPT-6.1 Sol measured |
| LiveBench data analysis | Not measured | 82.7% | Only GPT-6.1 Sol measured |
| Public Benefits Bench (Vals AI) | 62.9% | 59.3% | DeepSeek V4 Pro 0423 |
| SAGE (Vals AI) | Not measured | 46.5% | Only GPT-6.1 Sol measured |
| MedScribe (Vals AI) | 75.1% | 86.5% | GPT-6.1 Sol |
| Long context reasoning (AA-LCR) | Not measured | 84.0% | Only GPT-6.1 Sol measured |
| DTBench | 90.7% | 96.5% | GPT-6.1 Sol |
| LMCA | 41.2% | 62.8% | GPT-6.1 Sol |
| Surface Evolver Bench | 40.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Furniture assembly | Not measured | 80.0% | Only GPT-6.1 Sol measured |
| CL-bench Life | 13.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text | 1451 | 1443 | DeepSeek V4 Pro 0423 |
| LMArena Text: instruction following | 1445 | 1466 | GPT-6.1 Sol |
| LMArena Text: creative writing | 1446 | 1425 | DeepSeek V4 Pro 0423 |
| LMArena Vision | Not measured | 1288 | Only GPT-6.1 Sol measured |
| LMArena Text: English | 1459 | 1450 | DeepSeek V4 Pro 0423 |
| LMArena Text: non-English | 1439 | 1433 | DeepSeek V4 Pro 0423 |
| LMArena Text: Chinese | 1481 | 1487 | GPT-6.1 Sol |
| LMArena Text: German | 1458 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: Japanese | 1446 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: Korean | 1409 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: French | 1473 | 1460 | DeepSeek V4 Pro 0423 |
| LMArena Text: Spanish | 1457 | 1439 | DeepSeek V4 Pro 0423 |
| LMArena Text: Russian | 1453 | 1457 | GPT-6.1 Sol |
| LMArena Text: Polish | 1461 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: multi-turn | 1468 | 1442 | DeepSeek V4 Pro 0423 |
| LMArena Text: longer queries | 1458 | 1458 | GPT-6.1 Sol |
| LMArena Text: writing and language | 1447 | 1444 | DeepSeek V4 Pro 0423 |
| LMArena Text: entertainment and media | 1431 | 1426 | DeepSeek V4 Pro 0423 |
| LMArena Vision: English | Not measured | 1274 | Only GPT-6.1 Sol measured |
| LMArena Vision: reading text | Not measured | 1289 | Only GPT-6.1 Sol measured |
| LMArena Vision: creative writing | Not measured | 1301 | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Pro 0423 | GPT-6.1 Sol | 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 0423 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Pro 0423 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Pro 0423 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-6.1 Sol |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | April 24, 2026 | September 29, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.225 | $2.00 |
| Output $/Mtok | $2.716 | $10.00 |
| Coding index | 38.7 | 82.4 |
| Independent measurements behind it | 5 | 5 |
| Cost per solved task | $0.57 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Pro 0423 better than GPT-6.1 Sol for coding?
Pick GPT-6.1 Sol for coding: it scores 82.4 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423. Pick DeepSeek V4 Pro 0423 for output tokens 3.7x cheaper ($2.716 vs $10.00 per million) and work measured by Tax Agent Bench (Vals AI) or LMArena Text: hard prompts in English, where it leads.
Which is cheaper, DeepSeek V4 Pro 0423 or GPT-6.1 Sol?
DeepSeek V4 Pro 0423 costs $1.225 per million input tokens and $2.716 per million output tokens; GPT-6.1 Sol costs $2.00 and $10.00. Cost per solved task is known for DeepSeek V4 Pro 0423 only.
Which has the bigger context window, DeepSeek V4 Pro 0423 or GPT-6.1 Sol?
GPT-6.1 Sol, with 1.05M tokens against 1.05M.
How many benchmarks is the DeepSeek V4 Pro 0423 vs GPT-6.1 Sol comparison based on?
59 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0423's coding index rests on 5 independent benchmarks and GPT-6.1 Sol's on 5. Where only one model has a result, the page says so instead of naming a winner.