Model comparison
Claude 3.5 Sonnet vs DeepSeek-V3.1
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 34.4 on the Noometry Index.
Last verified . 23 shared benchmarks.
DeepSeekSummary
- They share 23 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 1 category and DeepSeek-V3.1 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1 leads 36.1 to 18.0.
- The biggest single-benchmark swing is DTBench: 67.8% for Claude 3.5 Sonnet and 82.7% for DeepSeek-V3.1.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | DeepSeek-V3.1 | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 34.4 | 42.2 |
| Released | 2024-06-20 | 2025-08-21 |
| Weights | Proprietary | Open |
| Context window | — | 164K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.95 |
| Results tracked | 60 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3.5 Sonnet: 39.5 (#145), DeepSeek-V3.1: 39.8 (#140)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| WeirdML | 40% | 38.4% |
| LMArena Coding | 1343 | 1417 |
| Aider Polyglot | 51.6% | — |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.1 (#61), DeepSeek-V3.1: —
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning DeepSeek-V3.1 leads
Claude 3.5 Sonnet: 22.5 (#176), DeepSeek-V3.1: 27.3 (#109)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| SimpleBench | 41.4% | 40% |
| LMArena Hard Prompts | 1305 | 1417 |
| DTBench | 67.8% | 82.7% |
| Epoch Capabilities Index | 133.55 | 139.92 |
| ForecastBench | 60.7 | 58 |
| Kagi LLM Benchmark | — | 53.2% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 24.3% |
| LiveBench | 59% | — |
Math DeepSeek-V3.1 leads
Claude 3.5 Sonnet: 18.0 (#282), DeepSeek-V3.1: 36.1 (#125)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Math | 1306 | 1420 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge DeepSeek-V3.1 leads
Claude 3.5 Sonnet: 28.5 (#236), DeepSeek-V3.1: 43.0 (#86)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Expert | 1264 | 1403 |
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 5.5% |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.0 (#115), DeepSeek-V3.1: —
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual DeepSeek-V3.1 leads
Claude 3.5 Sonnet: 43.4 (#180), DeepSeek-V3.1: 51.8 (#100)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Non-English | 1283 | 1400 |
| LMArena Chinese | 1271 | 1470 |
| LMArena French | 1304 | 1447 |
| LMArena German | 1297 | 1412 |
| LMArena Japanese | 1234 | 1374 |
| LMArena Korean | 1200 | 1337 |
| LMArena Russian | 1305 | 1405 |
| LMArena Spanish | 1289 | 1429 |
Instruction Following DeepSeek-V3.1 leads
Claude 3.5 Sonnet: 69.0 (#177), DeepSeek-V3.1: 74.1 (#105)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1400 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#162), DeepSeek-V3.1: 36.3 (#227)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Longer Query | 1311 | 1422 |
| Fiction.LiveBench | — | 52.8% |
Writing & Preference DeepSeek-V3.1 leads
Claude 3.5 Sonnet: 53.0 (#159), DeepSeek-V3.1: 60.5 (#93)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Text | 1298 | 1420 |
| LMArena Creative Writing | 1292 | 1401 |
| EQ-Bench Creative Writing | 1451 | 1436 |
| LMArena Multi-Turn | 1326 | 1408 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than DeepSeek-V3.1?
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 34.4 on the Noometry Index.
Is Claude 3.5 Sonnet or DeepSeek-V3.1 better for coding?
They score almost the same on coding (39.5 vs 39.8); test both on your own repository before choosing.
How many benchmarks do Claude 3.5 Sonnet and DeepSeek-V3.1 share?
23 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and DeepSeek-V3.1 has 27.