Model comparison
Claude 3.5 Sonnet vs DeepSeek-V3.1-Terminus
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 34.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeekSummary
- They share 11 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and DeepSeek-V3.1-Terminus in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 38.5 to 19.2.
- The biggest single-benchmark swing is DTBench: 67.8% for Claude 3.5 Sonnet and 81.3% for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | DeepSeek-V3.1-Terminus | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 34.6 | 43.1 |
| Released | 2024-06-20 | 2025-09-22 |
| Weights | Proprietary | Open |
| Context window | — | 164K |
| Max output | — | 147K |
| Input $ / M tokens | — | $0.27 |
| Output $ / M tokens | — | $1 |
| Results tracked | 60 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
Claude 3.5 Sonnet: 39.0 (#165), DeepSeek-V3.1-Terminus: 42.0 (#113)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Coding | 1342 | 1426 |
| Aider Polyglot | 51.6% | — |
| SciCode | — | 40.6% |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 745.17 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.3 (#67), DeepSeek-V3.1-Terminus: —
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1-Terminus |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning DeepSeek-V3.1-Terminus leads
Claude 3.5 Sonnet: 23.1 (#183), DeepSeek-V3.1-Terminus: 26.4 (#133)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1426 |
| DTBench | 67.8% | 81.3% |
| SimpleBench | 41.4% | — |
| Kagi LLM Benchmark | — | 57.4% |
| CritPt | — | 1.7% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 28.6% |
| Epoch Capabilities Index | 133.55 | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math DeepSeek-V3.1-Terminus leads
Claude 3.5 Sonnet: 19.2 (#288), DeepSeek-V3.1-Terminus: 38.5 (#137)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Math | 1307 | 1402 |
| 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 Not comparable
Claude 3.5 Sonnet: 28.6 (#245), DeepSeek-V3.1-Terminus: —
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1-Terminus |
|---|---|---|
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| LMArena Expert | 1265 | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), DeepSeek-V3.1-Terminus: —
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual DeepSeek-V3.1-Terminus leads
Claude 3.5 Sonnet: 43.2 (#185), DeepSeek-V3.1-Terminus: 52.1 (#92)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Non-English | 1283 | 1407 |
| LMArena Russian | 1306 | 1436 |
| LMArena Chinese | 1272 | — |
| LMArena French | 1305 | — |
| LMArena German | 1297 | — |
| LMArena Japanese | 1234 | — |
| LMArena Korean | 1200 | — |
| LMArena Spanish | 1290 | — |
Instruction Following DeepSeek-V3.1-Terminus leads
Claude 3.5 Sonnet: 68.8 (#182), DeepSeek-V3.1-Terminus: 74.0 (#106)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Instruction Following | 1297 | 1404 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context DeepSeek-V3.1-Terminus leads
Claude 3.5 Sonnet: 39.9 (#167), DeepSeek-V3.1-Terminus: 43.4 (#97)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Longer Query | 1311 | 1421 |
Writing & Preference DeepSeek-V3.1-Terminus leads
Claude 3.5 Sonnet: 52.9 (#164), DeepSeek-V3.1-Terminus: 61.0 (#92)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Text | 1298 | 1419 |
| LMArena Creative Writing | 1292 | 1403 |
| LMArena Multi-Turn | 1326 | 1411 |
| Short-Story Creative Writing | 80.3% | — |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than DeepSeek-V3.1-Terminus?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or DeepSeek-V3.1-Terminus better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and DeepSeek-V3.1-Terminus share?
11 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.