Claude Opus 4.6 vs DeepSeek V4 Pro
Claude Opus 4.6 
DeepSeek V4 Pro Verdict
- Claude Opus 4.6 and DeepSeek V4 Pro (max) are level on quality (63.7 vs 64.2).
- Claude Opus 4.6 is stronger in coding, human preference, maths, multimodal.
- DeepSeek V4 Pro (max) is stronger in agents & tools, reasoning, composite, instruction following, knowledge, long context.
- DeepSeek V4 Pro (max) is 18× cheaper ($0.544 vs $10.00 per 1M blended).
- DeepSeek V4 Pro (max) streams 2.4× faster (81 vs 34 tokens per second).
| Metric | Claude Opus 4.6 | DeepSeek V4 Pro (max) |
|---|---|---|
| BenchLeader Index | 63.7 | 64.2 |
| Agents & tools score | 67.8 | 70.2 |
| Coding score | 62.3 | 58.8 |
| Human preference score | 64.7 | – |
| Maths score | 68.7 | 53.7 |
| Multimodal score | 67.0 | – |
| Reasoning score | 62.6 | 70.9 |
| Composite score | – | 75.0 |
| Instruction following score | – | 74.3 |
| Knowledge score | – | 58.1 |
| Long context score | – | 66.6 |
| Blended price $/M | $10.00 | $0.544 |
| Output speed | 34 tok/s | 81 tok/s |
| Time to first answer | 1.7 s | 55.6 s |
| Context window | 1M | 1M |
| GPQA Diamond | 90.5% | 89.7% |
| FrontierMath Tiers 1–3 | – | 45.3% |
| FrontierMath Tier 4 | – | 2.4% |
| OTIS Mock AIME | 94.4% | 96.7% |
| SWE-bench Verified (Epoch) | 78.7% | 77.6% |
| SimpleQA Verified | – | 47.0% |
| Humanity's Last Exam | 19.0% | – |
| Terminal-Bench | 79.8% | – |
| SimpleBench | 67.6% | – |
| SciCode | – | 50.0% |
| Cybench | 93.0% | – |
| Remote Labor Index | 4.2% | – |
| WeirdML | 77.9% | 48.9% |
| APEX-Agents | 32.4% | – |
| FrontierCode | 26.6% | – |
| ProofBench | – | 16.0% |
| GSO-Bench | 33.3% | – |
| Epoch Capabilities Index | 155.3 | – |
| LMArena Text | 1497 | – |
| LMArena Hard Prompts | 1527 | – |
| LMArena Coding | 1546 | – |
| LMArena WebDev | 1537 | – |
| LMArena Vision | 1312 | – |
| AA Intelligence Index | – | 36.3 |
| IFBench | – | 76.5% |
| AA-LCR | – | 80.3% |
| AA-Omniscience | – | 0.8 |
| Terminal-Bench Hard | – | 46.2% |
| GPQA Diamond (AA) | – | 92.8% |
| Humanity's Last Exam (AA) | – | 41.0% |
| SciCode (AA) | – | 51.0% |
| τ²-Bench Telecom (AA) | – | 96.2% |
| LiveCodeBench | – | 87.5% |
| MMLU-Pro | – | 87.3% |
| LegalBench | – | 80.3% |
| CorpFin | – | 61.4% |
| TaxEval | – | 72.1% |
| SWE-bench (Vals) | – | 77.4% |
| GPQA Diamond (Vals) | – | 89.4% |
| Vals Index | – | 42.9 |
| AIME 2026 | – | 96.7% |
| HMMT February 2026 | – | 93.9% |
| MathArena Apex | – | 28.1% |
| HiL-Bench | 38.3% | – |
| EQ-Bench 4 | 1223 | – |
| Kagi LLM Benchmark | 72.4% | – |
| SWE-bench Verified (bash only) | 75.6% | – |
| SWE-bench Verified (any scaffold) | 75.6% | – |
| CritPt | – | 18.0% |
| GDPval (AA) | – | 49.7% |
| τ²-Bench Banking (AA) | – | 39.6% |
| ITBench SRE (AA) | – | 38.3% |
| Analyst Agent (AA) | – | 18.8% |
| APEX-Agents (AA) | – | 24.3% |
| CaseLaw v2 | – | 59.4% |
| Code Migration | – | 26.2% |
| Excel Modeling Benchmark | – | 51.6% |
| Finance Agent v2 | – | 44.1% |
| Harvey's Legal Agent Benchmark | – | 3.8% |
| Legal Research Bench | – | 23.1% |
| MedCode | 48.2% | 40.5% |
| MedScribe | 86.7% | 75.1% |
| ProgramBench | – | 0.0% |
| Public Benefits Bench | – | 62.9% |
| SkillsBench | – | 51.3% |
| Vibe Code Bench v1.1 | 57.6% | 49.9% |
| SWE Atlas: Codebase QnA | 33.3% | – |
| SWE Atlas: Refactoring | 35.6% | – |
| SWE Atlas: Test Writing | 36.7% | – |
| LMArena Maths | 1507 | – |
| LMArena Creative Writing | 1479 | – |
| LMArena Instruction Following | 1500 | – |
| LMArena Multi-turn | 1511 | – |
| LMArena Longer Queries | 1517 | – |
| LMArena Document | 1494 | – |
| Chess Puzzles | 17.0% | 20.0% |
| Mystery Game Puzzles | 15.0% | – |
| CL-bench | 20.7% | – |
| CL-bench Life | 13.6% | – |
| METR Time Horizons | 78.9% | – |
| LMCA | – | 41.2% |
| DTBench | – | 90.7% |
| ForecastBench | 60.0% | – |
| GBAEval | 44.1% | – |
| ALE-Bench | 996.5 | – |
| Vending-Bench 2 | 8017.6 | – |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
Claude Opus 4.6 vs DeepSeek V4 Pro: questions
- Is Claude Opus 4.6 better than DeepSeek V4 Pro?
- Claude Opus 4.6 and DeepSeek V4 Pro (max) are level on quality (63.7 vs 64.2). The BenchLeader Index combines every independent quality benchmark; DeepSeek V4 Pro (max) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Is Claude Opus 4.6 better than DeepSeek V4 Pro for coding?
- Claude Opus 4.6 scores higher in coding (62 vs 59 on the category index, where 50 is average).
- Is Claude Opus 4.6 better than DeepSeek V4 Pro for agentic tasks?
- DeepSeek V4 Pro scores higher in agentic tasks (70 vs 68 on the category index, where 50 is average).
- Which is cheaper, Claude Opus 4.6 or DeepSeek V4 Pro?
- DeepSeek V4 Pro is cheaper: $0.544 against $10.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Opus 4.6 or DeepSeek V4 Pro?
- DeepSeek V4 Pro streams faster: 81 against 34 output tokens per second.
- Which has the larger context window?
- Both accept 1M tokens of context.