Claude Opus 4.7 vs DeepSeek V4 Pro 0423
Claude Opus 4.7 leads DeepSeek V4 Pro 0423 on coding, 67.5 to 38.7 on the Vibe Coding Index, and DeepSeek V4 Pro 0423 costs 8.4x less per output token ($2.976 vs $25.00 per million). Updated October 22, 2026; 67 benchmarks have a result for both.
Claude Opus 4.7 or DeepSeek V4 Pro 0423: which to pick
Pick Claude Opus 4.7 for coding: it scores 67.5 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 4 benchmarks against 5.
Pick DeepSeek V4 Pro 0423 for output tokens 8.4x cheaper ($2.976 vs $25.00 per million) and a lower cost per solved task ($0.57 against $2.95).
- Shared results
- 67
- Claude Opus 4.7 only
- 36
- DeepSeek V4 Pro 0423 only
- 17
- Like-for-like categories
- 7 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
Claude Opus 4.7
Claude Opus 4.7 scores 67.5 against 38.7.
4 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Opus 4.7
Claude Opus 4.7 leads, 40.7 against 30.4.
Same board, both measured
Agentic work
AA Agentic Index
Claude Opus 4.7
Claude Opus 4.7 leads, 38.6 against 26.3.
Same board, both measured
Reasoning
GPQA Diamond
Claude Opus 4.7
Claude Opus 4.7 leads, 90.2% against 89.4%.
Same board, both measured
Math
AIME
No call
Only Claude Opus 4.7 has a AIME result, 96.3%.
Directional only
Knowledge
MMLU Pro
Claude Opus 4.7
Claude Opus 4.7 leads, 89.9% against 87.3%.
Same board, both measured
Web design
Design Arena: websites
No call
Only DeepSeek V4 Pro 0423 has a Design Arena: websites result, 1234.
Directional only
Long documents
Listed context window
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Pro 0423
Claude Opus 4.7 $0.018, DeepSeek V4 Pro 0423 $0.0028 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
DeepSeek V4 Pro 0423
Claude Opus 4.7 $2.95, DeepSeek V4 Pro 0423 $0.57.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Opus 4.7 67.5 from 4 benchmarks, DeepSeek V4 Pro 0423 38.7 from 5 benchmarks.
- Widest category
- Math, 18.6 points apart on average over 6 shared benchmarks.
- Widest single gap
- Vending-Bench 2: Claude Opus 4.7 $10,937 against DeepSeek V4 Pro 0423 $3,285, 47.8 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.7 $25.00 against DeepSeek V4 Pro 0423 $2.976 per million output tokens, 8.4x apart.
- Context window
- Claude Opus 4.7 takes 1M tokens, DeepSeek V4 Pro 0423 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 | Claude Opus 4.7 | Bars | DeepSeek V4 Pro 0423 | Ties |
|---|---|---|---|---|
| Coding | 12 | 1 | 1 tie | |
| Intelligence | 2 | 0 | ||
| Agentic work | 5 | 1 | ||
| Reasoning | 7 | 1 | ||
| Math | 6 | 0 | ||
| Knowledge | 11 | 0 | ||
| General | 20 | 0 | ||
| All shared boards | 63 | 3 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index121
| Benchmark | Claude Opus 4.7 | DeepSeek V4 Pro 0423 | Leader |
|---|---|---|---|
| LMArena WebDev | 1558 | 1447 | Claude Opus 4.7 |
| AA Coding Index | 73.6 | 59.4 | Claude Opus 4.7 |
| LiveCodeBench (Vals AI) | 85.1% | 87.5% | DeepSeek V4 Pro 0423 |
| SWE-bench Verified (Vals AI) | 82.0% | 77.4% | Claude Opus 4.7 |
| Terminal-Bench 4 (Vals AI) | Not measured | 11.1% | Only DeepSeek V4 Pro 0423 measured |
| Vibe Code Bench (Vals AI) | 71.0% | 49.9% | Claude Opus 4.7 |
| Code migration (Vals AI) | 43.9% | 26.2% | Claude Opus 4.7 |
| ProgramBench (Vals AI) | 0.0% | 0.0% | Tie |
| Terminal-Bench 2.1 (Vals AI) | 68.5% | 50.2% | Claude Opus 4.7 |
| SkillsBench (Vals AI) | Not measured | 51.3% | Only DeepSeek V4 Pro 0423 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 54.5% | Not measured | Only Claude Opus 4.7 measured |
| Terminal-Bench | 80.2% | Not measured | Only Claude Opus 4.7 measured |
| FrontierCode | 38.5% | 17.6% | Claude Opus 4.7 |
| GSO-Bench | 44.1% | Not measured | Only Claude Opus 4.7 measured |
| WeirdML | 76.4% | 48.9% | Claude Opus 4.7 |
| MirrorCode | 31.1% | Not measured | Only Claude Opus 4.7 measured |
| ALE-Bench | Not measured | 1006.1 | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: coding | 1519 | 1470 | Claude Opus 4.7 |
| LMArena Text: software and IT | 1516 | 1469 | Claude Opus 4.7 |
| LMArena WebDev: React | 1560 | 1441 | Claude Opus 4.7 |
| LMArena WebDev: HTML | 1554 | 1435 | Claude Opus 4.7 |
| LMArena WebDev: from an image | 1577 | Not measured | Only Claude Opus 4.7 measured |
| Neither model has a result on the other 17 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.7 | DeepSeek V4 Pro 0423 | Leader |
|---|---|---|---|
| AA Intelligence Index | 40.7 | 30.4 | Claude Opus 4.7 |
| Epoch Capabilities Index | 156.8 | 149.1 | Claude Opus 4.7 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | Claude Opus 4.7 | DeepSeek V4 Pro 0423 | Leader |
|---|---|---|---|
| AA Agentic Index | 38.6 | 26.3 | Claude Opus 4.7 |
| Design Arena: agents building web apps | Not measured | 1000 | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building full-stack apps | Not measured | 948 | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building Godot games | Not measured | 1059 | Only DeepSeek V4 Pro 0423 measured |
| Finance Agent (Vals AI) | 51.5% | 44.1% | Claude Opus 4.7 |
| Tax Agent Bench (Vals AI) | 23.7% | 25.2% | DeepSeek V4 Pro 0423 |
| Legal Research Bench (Vals AI) | 38.5% | 23.1% | Claude Opus 4.7 |
| Excel Modeling Benchmark (Vals AI) | 63.7% | 51.6% | Claude Opus 4.7 |
| τ²-Bench Telecom | 88.6% | Not measured | Only Claude Opus 4.7 measured |
| APEX-Agents | 49.2% | Not measured | Only Claude Opus 4.7 measured |
| OSWorld 2.0 | 18.2% | Not measured | Only Claude Opus 4.7 measured |
| PostTrainBench | 28.6% | Not measured | Only Claude Opus 4.7 measured |
| Vending-Bench 2 | $10,937 | $3,285 | Claude Opus 4.7 |
| LMArena Search | 1230 | Not measured | Only Claude Opus 4.7 measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index71
| Benchmark | Claude Opus 4.7 | DeepSeek V4 Pro 0423 | Leader |
|---|---|---|---|
| GPQA Diamond | 90.2% | 89.4% | Claude Opus 4.7 |
| MMMU Pro (Vals AI) | 85.5% | Not measured | Only Claude Opus 4.7 measured |
| GPQA Diamond (Artificial Analysis run) | 91.4% | Not measured | Only Claude Opus 4.7 measured |
| Humanity's Last Exam (Artificial Analysis run) | 42.3% | Not measured | Only Claude Opus 4.7 measured |
| GPQA Diamond (Epoch AI run) | 90.2% | 90.9% | DeepSeek V4 Pro 0423 |
| ARC-AGI | 93.5% | Not measured | Only Claude Opus 4.7 measured |
| ARC-AGI-2 | 75.8% | Not measured | Only Claude Opus 4.7 measured |
| SimpleBench | 61.7% | Not measured | Only Claude Opus 4.7 measured |
| Chess puzzles | 41.0% | 19.0% | Claude Opus 4.7 |
| Mystery game puzzles | 28.0% | 17.0% | Claude Opus 4.7 |
| EBR-bench | 19.0% | Not measured | Only Claude Opus 4.7 measured |
| LMArena Text: hard prompts | 1506 | 1461 | Claude Opus 4.7 |
| LMArena Text: expert | 1521 | 1463 | Claude Opus 4.7 |
| LMArena Text: hard prompts in English | 1508 | 1466 | Claude Opus 4.7 |
| LMArena Vision: diagrams | 1336 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Vision: homework | 1337 | Not measured | Only Claude Opus 4.7 measured |
| Kagi LLM Benchmark | 80.7% | 53.5% | Claude Opus 4.7 |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Claude Opus 4.7 | DeepSeek V4 Pro 0423 | Leader |
|---|---|---|---|
| AIME | 96.3% | Not measured | Only Claude Opus 4.7 measured |
| OTIS Mock AIME | 97.8% | 96.7% | Claude Opus 4.7 |
| FrontierMath, tiers 1 to 3 | 70.2% | 45.3% | Claude Opus 4.7 |
| FrontierMath, tier 4 | 31.7% | 2.4% | Claude Opus 4.7 |
| ProofBench | 54.0% | 16.0% | Claude Opus 4.7 |
| LMArena Text: math | 1498 | 1443 | Claude Opus 4.7 |
| LMArena Text: mathematical work | 1509 | 1455 | Claude Opus 4.7 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index110
| Benchmark | Claude Opus 4.7 | DeepSeek V4 Pro 0423 | Leader |
|---|---|---|---|
| MMLU Pro | 89.9% | 87.3% | Claude Opus 4.7 |
| LegalBench (Vals AI) | 85.3% | 80.3% | Claude Opus 4.7 |
| CaseLaw (Vals AI) | 68.4% | 59.4% | Claude Opus 4.7 |
| CorpFin (Vals AI) | 66.1% | 61.4% | Claude Opus 4.7 |
| TaxEval (Vals AI) | 75.3% | 72.1% | Claude Opus 4.7 |
| MortgageTax (Vals AI) | 70.3% | Not measured | Only Claude Opus 4.7 measured |
| MedCode (Vals AI) | 54.9% | 40.5% | Claude Opus 4.7 |
| SimpleQA Verified | 51.7% | 47.0% | Claude Opus 4.7 |
| LMArena Text: science | 1508 | 1470 | Claude Opus 4.7 |
| LMArena Text: medicine and healthcare | 1495 | 1466 | Claude Opus 4.7 |
| LMArena Text: legal and government | 1504 | 1464 | Claude Opus 4.7 |
| LMArena Text: business and finance | 1490 | 1443 | Claude Opus 4.7 |
| FACTS Benchmark Suite | 45.5% | Not measured | Only Claude Opus 4.7 measured |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Claude Opus 4.7 | DeepSeek V4 Pro 0423 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1234 | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: UI components | Not measured | 1219 | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: game dev | Not measured | 1228 | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: data viz | Not measured | 1203 | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: 3D | Not measured | 1253 | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: all code categories | Not measured | 1240 | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: SVG | Not measured | 1139 | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: ASCII art | Not measured | 1149 | Only DeepSeek V4 Pro 0423 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index200
| Benchmark | Claude Opus 4.7 | DeepSeek V4 Pro 0423 | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | Not measured | 62.9% | Only DeepSeek V4 Pro 0423 measured |
| SAGE (Vals AI) | 56.1% | Not measured | Only Claude Opus 4.7 measured |
| MedScribe (Vals AI) | 83.0% | 75.1% | Claude Opus 4.7 |
| Vals Multimodal Index | 67.4% | Not measured | Only Claude Opus 4.7 measured |
| IFBench | 58.6% | Not measured | Only Claude Opus 4.7 measured |
| Long context reasoning (AA-LCR) | 78.7% | Not measured | Only Claude Opus 4.7 measured |
| DTBench | 94.7% | 90.7% | Claude Opus 4.7 |
| LMCA | 52.2% | 41.2% | Claude Opus 4.7 |
| Surface Evolver Bench | Not measured | 40.0% | Only DeepSeek V4 Pro 0423 measured |
| Furniture assembly | 33.3% | Not measured | Only Claude Opus 4.7 measured |
| ExploitBench | 26.5% | Not measured | Only Claude Opus 4.7 measured |
| CL-bench Life | Not measured | 13.5% | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text | 1490 | 1451 | Claude Opus 4.7 |
| LMArena Text: instruction following | 1498 | 1445 | Claude Opus 4.7 |
| LMArena Text: creative writing | 1486 | 1446 | Claude Opus 4.7 |
| LMArena Vision | 1317 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Text: English | 1496 | 1459 | Claude Opus 4.7 |
| LMArena Text: non-English | 1480 | 1439 | Claude Opus 4.7 |
| LMArena Text: Chinese | 1531 | 1481 | Claude Opus 4.7 |
| LMArena Text: German | 1495 | 1458 | Claude Opus 4.7 |
| LMArena Text: Japanese | 1474 | 1446 | Claude Opus 4.7 |
| LMArena Text: Korean | 1464 | 1409 | Claude Opus 4.7 |
| LMArena Text: French | 1503 | 1473 | Claude Opus 4.7 |
| LMArena Text: Spanish | 1494 | 1457 | Claude Opus 4.7 |
| LMArena Text: Russian | 1494 | 1453 | Claude Opus 4.7 |
| LMArena Text: Polish | 1489 | 1461 | Claude Opus 4.7 |
| LMArena Text: multi-turn | 1505 | 1468 | Claude Opus 4.7 |
| LMArena Text: longer queries | 1505 | 1458 | Claude Opus 4.7 |
| LMArena Text: writing and language | 1492 | 1447 | Claude Opus 4.7 |
| LMArena Text: entertainment and media | 1474 | 1431 | Claude Opus 4.7 |
| LMArena Vision: English | 1322 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Vision: Chinese | 1371 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Vision: reading text | 1327 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Vision: humor | 1309 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Vision: recognizing things | 1278 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Vision: creative writing | 1326 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Document | 1495 | Not measured | Only Claude Opus 4.7 measured |
| Neither model has a result on the other 9 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Opus 4.7 | DeepSeek V4 Pro 0423 | 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 | Anthropic Claude Opus 4.7 | DeepSeek V4 Pro 0423 |
|---|---|---|
| Maker | Anthropic | DeepSeek |
| Weights | No public weights listed | Open weights |
| Released | April 16, 2026 | April 24, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $5.00 | $1.358 |
| Output $/Mtok | $25.00 | $2.976 |
| Coding index | 67.5 | 38.7 |
| Independent measurements behind it | 4 | 5 |
| Cost per solved task | $2.95 | $0.57 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.7 better than DeepSeek V4 Pro 0423 for coding?
Pick Claude Opus 4.7 for coding: it scores 67.5 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 4 benchmarks against 5. Pick DeepSeek V4 Pro 0423 for output tokens 8.4x cheaper ($2.976 vs $25.00 per million) and a lower cost per solved task ($0.57 against $2.95).
Which is cheaper, Claude Opus 4.7 or DeepSeek V4 Pro 0423?
Claude Opus 4.7 costs $5.00 per million input tokens and $25.00 per million output tokens; DeepSeek V4 Pro 0423 costs $1.358 and $2.976. Per solved SWE-bench Verified task, Claude Opus 4.7 costs $2.95 and DeepSeek V4 Pro 0423 $0.57.
Which has the bigger context window, Claude Opus 4.7 or DeepSeek V4 Pro 0423?
DeepSeek V4 Pro 0423, with 1.05M tokens against 1M.
How many benchmarks is the Claude Opus 4.7 vs DeepSeek V4 Pro 0423 comparison based on?
67 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.7's coding index rests on 4 independent benchmarks and DeepSeek V4 Pro 0423's on 5. Where only one model has a result, the page says so instead of naming a winner.