Claude Sonnet 5 vs DeepSeek V4 Pro
Claude Sonnet 5 
DeepSeek V4 Pro Verdict
- DeepSeek V4 Pro (max) leads on quality: 64.2 vs 62.2.
- Claude Sonnet 5 (high) is stronger in coding, human preference, knowledge, maths, multimodal.
- DeepSeek V4 Pro (max) is stronger in agents & tools, composite, long context, reasoning, instruction following.
- DeepSeek V4 Pro (max) is 7.4× cheaper ($0.544 vs $4.00 per 1M blended).
| Metric | Claude Sonnet 5 (high) | DeepSeek V4 Pro (max) |
|---|---|---|
| BenchLeader Index | 62.2 | 64.2 |
| Agents & tools score | 62.0 | 70.2 |
| Coding score | 61.5 | 58.8 |
| Composite score | 69.6 | 75.0 |
| Human preference score | 65.9 | – |
| Knowledge score | 62.4 | 58.1 |
| Long context score | 64.7 | 66.6 |
| Maths score | 66.9 | 53.7 |
| Multimodal score | 62.6 | – |
| Reasoning score | 69.6 | 70.9 |
| Instruction following score | – | 74.3 |
| Blended price $/M | $4.00 | $0.544 |
| Output speed | 64 tok/s | 81 tok/s |
| Time to first answer | 2.9 s | 55.6 s |
| Context window | 1M | 1M |
| GPQA Diamond | – | 89.7% |
| FrontierMath Tiers 1–3 | – | 45.3% |
| FrontierMath Tier 4 | – | 2.4% |
| OTIS Mock AIME | – | 96.7% |
| SWE-bench Verified (Epoch) | – | 77.6% |
| SimpleQA Verified | – | 47.0% |
| SciCode | 48.6% | 50.0% |
| WeirdML | 68.8% | 48.9% |
| ProofBench | – | 16.0% |
| LMArena Text | 1461 | – |
| LMArena Hard Prompts | 1489 | – |
| LMArena Coding | 1521 | – |
| LMArena WebDev | 1537 | – |
| LMArena Vision | 1277 | – |
| LMArena Agent | 6 | – |
| AA Intelligence Index | 32.0 | 36.3 |
| IFBench | – | 76.5% |
| AA-LCR | 76.7% | 80.3% |
| AA-Omniscience | -3.7 | 0.8 |
| Terminal-Bench Hard | – | 46.2% |
| GPQA Diamond (AA) | – | 92.8% |
| Humanity's Last Exam (AA) | 35.7% | 41.0% |
| SciCode (AA) | 54.3% | 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% |
| CritPt | 15.1% | 18.0% |
| GDPval (AA) | 40.4% | 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 | – | 40.5% |
| MedScribe | – | 75.1% |
| ProgramBench | – | 0.0% |
| Public Benefits Bench | – | 62.9% |
| SkillsBench | – | 51.3% |
| Vibe Code Bench v1.1 | – | 49.9% |
| LMArena Maths | 1476 | – |
| LMArena Creative Writing | 1437 | – |
| LMArena Instruction Following | 1465 | – |
| LMArena Multi-turn | 1473 | – |
| LMArena Longer Queries | 1482 | – |
| LMArena Document | 1476 | – |
| Chess Puzzles | – | 20.0% |
| DeepSWE | 48.2% | – |
| LMCA | – | 41.2% |
| DTBench | – | 90.7% |
| CursorBench | 56.9% | – |
| ALE-Bench | 1463.1 | – |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
Claude Sonnet 5 vs DeepSeek V4 Pro: questions
- Is Claude Sonnet 5 better than DeepSeek V4 Pro?
- DeepSeek V4 Pro (max) leads on quality: 64.2 vs 62.2. 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 Sonnet 5 better than DeepSeek V4 Pro for coding?
- Claude Sonnet 5 scores higher in coding (62 vs 59 on the category index, where 50 is average).
- Is Claude Sonnet 5 better than DeepSeek V4 Pro for agentic tasks?
- DeepSeek V4 Pro scores higher in agentic tasks (70 vs 62 on the category index, where 50 is average).
- Which is cheaper, Claude Sonnet 5 or DeepSeek V4 Pro?
- DeepSeek V4 Pro is cheaper: $0.544 against $4.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Sonnet 5 or DeepSeek V4 Pro?
- DeepSeek V4 Pro streams faster: 81 against 64 output tokens per second.
- Which has the larger context window?
- Both accept 1M tokens of context.