Claude Opus 4.8 vs DeepSeek V3.2 Exp
Updated October 21, 2026. 48 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
vs boards won of 48 shared
Decision reading
Pick Claude Opus 4.8 for coding: it scores 66.0 on the Vibe Coding Index against 55.0 for DeepSeek V3.2 Exp.
Pick DeepSeek V3.2 Exp when output tokens cost 61.0x less, or when the benchmark that matters is LMArena Text: medicine and healthcare, where it leads.
Model AClaude Opus 4.8Anthropic66.0/1002 independent benchmarks$2.17 per solved taskModel BDeepSeek V3.2 ExpDeepSeek55.0/1002 independent benchmarksNo cost per solved task
- Shared results
- 48
- Claude Opus 4.8 only
- 78
- DeepSeek V3.2 Exp only
- 9
- Like-for-like categories
- 8 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
Claude Opus 4.8
Claude Opus 4.8 scores 66.0 against 55.0.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
Claude Opus 4.8
Claude Opus 4.8 leads, 41.8 against 16.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Opus 4.8 has a AA Agentic Index result, 41.9.
Directional only
Reasoning
GPQA Diamond
No call
Only Claude Opus 4.8 has a GPQA Diamond result, 92.4%.
Directional only
Knowledge
MMLU Pro
No call
Only Claude Opus 4.8 has a MMLU Pro result, 89.6%.
Directional only
Web design
Design Arena: websites
Claude Opus 4.8
Claude Opus 4.8 leads, 1258 against 1179.
Same board, both measured
Long documents
Listed context window
Claude Opus 4.8
Claude Opus 4.8 takes 1M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.2 Exp
Claude Opus 4.8 $0.018, DeepSeek V3.2 Exp $0.0005 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Claude Opus 4.8 has the number, $2.17.
Directional only
At a glance
- Coding index
- Claude Opus 4.8 66.0 from 2 benchmarks, DeepSeek V3.2 Exp 55.0 from 2 benchmarks.
- Widest category
- Agentic work, 60.5 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Claude Opus 4.8 94.4% against DeepSeek V3.2 Exp 33.9%, 60.5 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.8 $25.00 against DeepSeek V3.2 Exp $0.41 per million output tokens, 61.0x apart.
- Context window
- Claude Opus 4.8 takes 1M tokens, DeepSeek V3.2 Exp 164K.
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 4.8 | Bars | DeepSeek V3.2 Exp | Ties |
|---|---|---|---|---|
| Coding | 6 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 5 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 3 | 1 | ||
| Web design | 7 | 0 | ||
| General | 21 | 0 | ||
| All shared boards | 47 | 1 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index60
| Benchmark | Claude Opus 4.8 | DeepSeek V3.2 Exp | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 74.2% | Only DeepSeek V3.2 Exp measured |
| LiveBench coding | 77.3% | Not measured | Only Claude Opus 4.8 measured |
| LMArena WebDev | 1556 | 1272 | Claude Opus 4.8 |
| AA Coding Index | 74.3 | Not measured | Only Claude Opus 4.8 measured |
| LiveCodeBench (Vals AI) | 87.8% | Not measured | Only Claude Opus 4.8 measured |
| SWE-bench Verified (Vals AI) | 88.6% | Not measured | Only Claude Opus 4.8 measured |
| Terminal-Bench 4 (Vals AI) | 23.2% | Not measured | Only Claude Opus 4.8 measured |
| Vibe Code Bench (Vals AI) | 82.7% | Not measured | Only Claude Opus 4.8 measured |
| Code migration (Vals AI) | 47.3% | Not measured | Only Claude Opus 4.8 measured |
| ProgramBench (Vals AI) | 1.0% | Not measured | Only Claude Opus 4.8 measured |
| Terminal-Bench 2.1 (Vals AI) | 71.9% | Not measured | Only Claude Opus 4.8 measured |
| SkillsBench (Vals AI) | 59.2% | Not measured | Only Claude Opus 4.8 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 78.9% | Only DeepSeek V3.2 Exp measured |
| SciCode | 54.4% | Not measured | Only Claude Opus 4.8 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 58.3% | 31.1% | Claude Opus 4.8 |
| FrontierCode | 46.5% | Not measured | Only Claude Opus 4.8 measured |
| GSO-Bench | 47.1% | Not measured | Only Claude Opus 4.8 measured |
| WeirdML | 82.9% | 39.5% | Claude Opus 4.8 |
| LMArena Text: coding | 1490 | 1438 | Claude Opus 4.8 |
| LMArena Text: software and IT | 1488 | 1438 | Claude Opus 4.8 |
| LMArena WebDev: React | 1557 | Not measured | Only Claude Opus 4.8 measured |
| LMArena WebDev: HTML | 1543 | 1281 | Claude Opus 4.8 |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.8 | DeepSeek V3.2 Exp | Leader |
|---|---|---|---|
| AA Intelligence Index | 41.8 | 16.6 | Claude Opus 4.8 |
| Epoch Capabilities Index | 159.0 | 144.9 | Claude Opus 4.8 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Opus 4.8 | DeepSeek V3.2 Exp | Leader |
|---|---|---|---|
| AA Agentic Index | 41.9 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: agents building web apps | 1233 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: agents building full-stack apps | 1249 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: agents building mobile apps | 1222 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: agents building Android apps | 1237 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: agents building Godot games | 1231 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: agents building games | 1238 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: HTML slides | 1221 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: PowerPoint slides | 1227 | Not measured | Only Claude Opus 4.8 measured |
| LiveBench research | 81.8% | Not measured | Only Claude Opus 4.8 measured |
| LiveBench browser | 96.0% | Not measured | Only Claude Opus 4.8 measured |
| LiveBench long agentic | 48.3% | Not measured | Only Claude Opus 4.8 measured |
| Finance Agent (Vals AI) | 53.9% | Not measured | Only Claude Opus 4.8 measured |
| Tax Agent Bench (Vals AI) | 30.0% | Not measured | Only Claude Opus 4.8 measured |
| Legal Research Bench (Vals AI) | 43.8% | Not measured | Only Claude Opus 4.8 measured |
| Excel Modeling Benchmark (Vals AI) | 69.4% | Not measured | Only Claude Opus 4.8 measured |
| Terminal-Bench-Science (Vals AI) | 4.3% | Not measured | Only Claude Opus 4.8 measured |
| Time Horizon Index (Vals AI) | 11.8% | Not measured | Only Claude Opus 4.8 measured |
| τ²-Bench Telecom | 94.4% | 33.9% | Claude Opus 4.8 |
| APEX-Agents | 48.9% | Not measured | Only Claude Opus 4.8 measured |
| Remote Labor Index | 8.3% | Not measured | Only Claude Opus 4.8 measured |
| OSWorld 2.0 | 20.6% | Not measured | Only Claude Opus 4.8 measured |
| DeepResearch Bench | 50.2% | Not measured | Only Claude Opus 4.8 measured |
| PostTrainBench | 33.8% | Not measured | Only Claude Opus 4.8 measured |
| TheAgentCompany | Not measured | 42.9% | Only DeepSeek V3.2 Exp measured |
| Vending-Bench 2 | $5,787 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Search | 1204 | Not measured | Only Claude Opus 4.8 measured |
| Neither model has a result on the other 12 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Claude Opus 4.8 | DeepSeek V3.2 Exp | Leader |
|---|---|---|---|
| GPQA Diamond | 92.4% | Not measured | Only Claude Opus 4.8 measured |
| LiveBench reasoning | 89.2% | Not measured | Only Claude Opus 4.8 measured |
| MMMU Pro (Vals AI) | 86.6% | Not measured | Only Claude Opus 4.8 measured |
| GPQA Diamond (Artificial Analysis run) | 92.0% | 79.7% | Claude Opus 4.8 |
| Humanity's Last Exam (Artificial Analysis run) | 48.7% | 14.9% | Claude Opus 4.8 |
| GPQA Diamond (Epoch AI run) | 91.0% | Not measured | Only Claude Opus 4.8 measured |
| ARC-AGI | 92.5% | Not measured | Only Claude Opus 4.8 measured |
| ARC-AGI-2 | 72.1% | Not measured | Only Claude Opus 4.8 measured |
| SimpleBench | 64.8% | Not measured | Only Claude Opus 4.8 measured |
| Chess puzzles | 52.0% | Not measured | Only Claude Opus 4.8 measured |
| Mystery game puzzles | 36.0% | Not measured | Only Claude Opus 4.8 measured |
| EBR-bench | 28.6% | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: hard prompts | 1482 | 1429 | Claude Opus 4.8 |
| LMArena Text: expert | 1503 | 1422 | Claude Opus 4.8 |
| LMArena Text: hard prompts in English | 1487 | 1444 | Claude Opus 4.8 |
| LMArena Vision: diagrams | 1315 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision: homework | 1337 | Not measured | Only Claude Opus 4.8 measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.8 | DeepSeek V3.2 Exp | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 87.7 | Only DeepSeek V3.2 Exp measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 87.7% | Only DeepSeek V3.2 Exp measured |
| OTIS Mock AIME | 98.3% | Not measured | Only Claude Opus 4.8 measured |
| FrontierMath, tiers 1 to 3 | 80.0% | Not measured | Only Claude Opus 4.8 measured |
| FrontierMath, tier 4 | 56.1% | Not measured | Only Claude Opus 4.8 measured |
| ProofBench | 69.0% | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: math | 1486 | 1422 | Claude Opus 4.8 |
| LMArena Text: mathematical work | 1497 | 1433 | Claude Opus 4.8 |
| Neither model has a result on the other 5 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | Claude Opus 4.8 | DeepSeek V3.2 Exp | Leader |
|---|---|---|---|
| MMLU Pro | 89.6% | Not measured | Only Claude Opus 4.8 measured |
| LegalBench (Vals AI) | 83.6% | Not measured | Only Claude Opus 4.8 measured |
| CorpFin (Vals AI) | 66.7% | Not measured | Only Claude Opus 4.8 measured |
| TaxEval (Vals AI) | 75.6% | Not measured | Only Claude Opus 4.8 measured |
| MortgageTax (Vals AI) | 69.9% | Not measured | Only Claude Opus 4.8 measured |
| MedCode (Vals AI) | 53.2% | Not measured | Only Claude Opus 4.8 measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 85.0% | Only DeepSeek V3.2 Exp measured |
| SimpleQA Verified | 53.0% | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: science | 1477 | 1443 | Claude Opus 4.8 |
| LMArena Text: medicine and healthcare | 1464 | 1468 | DeepSeek V3.2 Exp |
| LMArena Text: legal and government | 1477 | 1419 | Claude Opus 4.8 |
| LMArena Text: business and finance | 1458 | 1412 | Claude Opus 4.8 |
| Neither model has a result on the other 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | Claude Opus 4.8 | DeepSeek V3.2 Exp | Leader |
|---|---|---|---|
| Design Arena: websites | 1258 | 1179 | Claude Opus 4.8 |
| Design Arena: UI components | 1256 | 1166 | Claude Opus 4.8 |
| Design Arena: game dev | 1264 | 1145 | Claude Opus 4.8 |
| Design Arena: data viz | 1240 | 1152 | Claude Opus 4.8 |
| Design Arena: 3D | 1223 | 1148 | Claude Opus 4.8 |
| Design Arena: all code categories | 1255 | 1171 | Claude Opus 4.8 |
| Design Arena: SVG | 1194 | 1031 | Claude Opus 4.8 |
| Design Arena: ASCII art | 1276 | Not measured | Only Claude Opus 4.8 measured |
| LiveBench design | 78.8% | Not measured | Only Claude Opus 4.8 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index210
| Benchmark | Claude Opus 4.8 | DeepSeek V3.2 Exp | Leader |
|---|---|---|---|
| LiveBench data analysis | 66.0% | Not measured | Only Claude Opus 4.8 measured |
| Public Benefits Bench (Vals AI) | 68.1% | Not measured | Only Claude Opus 4.8 measured |
| SAGE (Vals AI) | 54.8% | Not measured | Only Claude Opus 4.8 measured |
| MedScribe (Vals AI) | 85.8% | Not measured | Only Claude Opus 4.8 measured |
| Vals Multimodal Index | 70.9% | Not measured | Only Claude Opus 4.8 measured |
| IFBench | 62.2% | 54.1% | Claude Opus 4.8 |
| Long context reasoning (AA-LCR) | 77.7% | 72.3% | Claude Opus 4.8 |
| DTBench | 94.9% | 87.7% | Claude Opus 4.8 |
| LMCA | 57.5% | 29.1% | Claude Opus 4.8 |
| Fiction.LiveBench | Not measured | 83.3% | Only DeepSeek V3.2 Exp measured |
| CL-bench | Not measured | 13.2% | Only DeepSeek V3.2 Exp measured |
| Surface Evolver Bench | 87.5% | Not measured | Only Claude Opus 4.8 measured |
| Furniture assembly | 42.5% | Not measured | Only Claude Opus 4.8 measured |
| CL-bench Life | Not measured | 9.5% | Only DeepSeek V3.2 Exp measured |
| LMArena Text | 1461 | 1425 | Claude Opus 4.8 |
| LMArena Text: instruction following | 1476 | 1401 | Claude Opus 4.8 |
| LMArena Text: creative writing | 1454 | 1404 | Claude Opus 4.8 |
| LMArena Vision | 1294 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: English | 1468 | 1441 | Claude Opus 4.8 |
| LMArena Text: non-English | 1450 | 1404 | Claude Opus 4.8 |
| LMArena Text: Chinese | 1506 | 1461 | Claude Opus 4.8 |
| LMArena Text: German | 1472 | 1440 | Claude Opus 4.8 |
| LMArena Text: Japanese | 1442 | 1331 | Claude Opus 4.8 |
| LMArena Text: Korean | 1431 | 1372 | Claude Opus 4.8 |
| LMArena Text: French | 1481 | 1434 | Claude Opus 4.8 |
| LMArena Text: Spanish | 1465 | 1441 | Claude Opus 4.8 |
| LMArena Text: Russian | 1474 | 1412 | Claude Opus 4.8 |
| LMArena Text: Polish | 1459 | 1435 | Claude Opus 4.8 |
| LMArena Text: multi-turn | 1476 | 1422 | Claude Opus 4.8 |
| LMArena Text: longer queries | 1483 | 1418 | Claude Opus 4.8 |
| LMArena Text: writing and language | 1461 | 1407 | Claude Opus 4.8 |
| LMArena Text: entertainment and media | 1440 | 1407 | Claude Opus 4.8 |
| LMArena Vision: English | 1293 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision: Chinese | 1346 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision: reading text | 1303 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision: humor | 1282 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision: creative writing | 1301 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Document | 1475 | Not measured | Only Claude Opus 4.8 measured |
| Neither model has a result on the other 8 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Opus 4.8 | DeepSeek V3.2 Exp | 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
Claude Opus 4.8$0.018Fits in one request
DeepSeek V3.2 Exp$0.0005Fits in one request
DeepSeek V3.2 Exp costs less
Repository review
50K input + 3K output tokens
Claude Opus 4.8$0.325Fits in one request
DeepSeek V3.2 Exp$0.015Fits in one request
DeepSeek V3.2 Exp costs less
Agent loop
200K input + 10K output tokens
Claude Opus 4.8$1.25Fits in one request
DeepSeek V3.2 Exp$0.058Exceeds the context window
DeepSeek V3.2 Exp 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 4.8 | DeepSeek V3.2 Exp |
|---|---|---|
| Maker | Anthropic | DeepSeek |
| Weights | No public weights listed | Open weights |
| Released | May 27, 2026 | September 29, 2025 |
| Context window | 1M | 164K |
| Input $/Mtok | $5.00 | $0.27 |
| Output $/Mtok | $25.00 | $0.41 |
| Coding index | 66.0 | 55.0 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | $2.17 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.8 better than DeepSeek V3.2 Exp for coding?
Pick Claude Opus 4.8 for coding: it scores 66.0 on the Vibe Coding Index against 55.0 for DeepSeek V3.2 Exp. Pick DeepSeek V3.2 Exp when output tokens cost 61.0x less, or when the benchmark that matters is LMArena Text: medicine and healthcare, where it leads.
Which is cheaper, Claude Opus 4.8 or DeepSeek V3.2 Exp?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; DeepSeek V3.2 Exp costs $0.27 and $0.41. Cost per solved task is known for Claude Opus 4.8 only.
Which has the bigger context window, Claude Opus 4.8 or DeepSeek V3.2 Exp?
Claude Opus 4.8, with 1M tokens against 164K.
How many benchmarks is the Claude Opus 4.8 vs DeepSeek V3.2 Exp comparison based on?
48 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.8's coding index rests on 2 independent benchmarks and DeepSeek V3.2 Exp's on 2. Where only one model has a result, the page says so instead of naming a winner.