Model comparison
Claude Sonnet 4 vs DeepSeek-V3.1-Terminus
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 40.6 on the Noometry Index.
Last verified . 16 shared benchmarks.
DeepSeekSummary
- They share 16 benchmarks with published results for both. Claude Sonnet 4 scores higher in 2 categories and DeepSeek-V3.1-Terminus in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where DeepSeek-V3.1-Terminus leads 43.5 to 33.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 73% for Claude Sonnet 4 and 57.4% for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Claude Sonnet 4 accepts more context: 200K tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | DeepSeek-V3.1-Terminus | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 40.6 | 42.6 |
| Released | 2025-05-22 | 2025-09-22 |
| Weights | Proprietary | Open |
| Context window | 200K | 164K |
| Max output | 64K | 66K |
| Input $ / M tokens | $3 | $0.30 |
| Output $ / M tokens | $15 | $1 |
| Results tracked | 58 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 44.0 (#70), DeepSeek-V3.1-Terminus: 41.5 (#114)
| Benchmark | Claude Sonnet 4 | DeepSeek-V3.1-Terminus |
|---|---|---|
| SciCode | 40% | 40.6% |
| LMArena Coding | 1414 | 1426 |
| ALE-Bench | 655.35 | 745.17 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.3 (#29), DeepSeek-V3.1-Terminus: —
| Benchmark | Claude Sonnet 4 | DeepSeek-V3.1-Terminus |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning DeepSeek-V3.1-Terminus leads
Claude Sonnet 4: 23.0 (#169), DeepSeek-V3.1-Terminus: 25.7 (#126)
| Benchmark | Claude Sonnet 4 | DeepSeek-V3.1-Terminus |
|---|---|---|
| Kagi LLM Benchmark | 73% | 57.4% |
| CritPt | 0.3% | 1.7% |
| LMArena Hard Prompts | 1372 | 1427 |
| DTBench | 77.1% | 81.3% |
| LMCA | 29% | 28.6% |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| ARC-AGI-1 | 40% | — |
| EnigmaEval | 3.1% | — |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 41.5 (#71), DeepSeek-V3.1-Terminus: 35.7 (#138)
| Benchmark | Claude Sonnet 4 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Math | 1375 | 1402 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Not comparable
Claude Sonnet 4: 41.6 (#99), DeepSeek-V3.1-Terminus: —
| Benchmark | Claude Sonnet 4 | DeepSeek-V3.1-Terminus |
|---|---|---|
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
| LMArena Expert | 1371 | — |
Multimodal Not comparable
Claude Sonnet 4: 25.6 (#116), DeepSeek-V3.1-Terminus: —
| Benchmark | Claude Sonnet 4 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual DeepSeek-V3.1-Terminus leads
Claude Sonnet 4: 46.9 (#151), DeepSeek-V3.1-Terminus: 52.3 (#87)
| Benchmark | Claude Sonnet 4 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Non-English | 1333 | 1407 |
| LMArena Russian | 1355 | 1434 |
| LMArena Chinese | 1351 | — |
| LMArena French | 1364 | — |
| LMArena German | 1331 | — |
| LMArena Japanese | 1301 | — |
| LMArena Korean | 1293 | — |
| LMArena Spanish | 1356 | — |
Instruction Following DeepSeek-V3.1-Terminus leads
Claude Sonnet 4: 71.8 (#141), DeepSeek-V3.1-Terminus: 74.4 (#96)
| Benchmark | Claude Sonnet 4 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Instruction Following | 1375 | 1406 |
| IFEval | 84% | — |
Long Context DeepSeek-V3.1-Terminus leads
Claude Sonnet 4: 33.6 (#254), DeepSeek-V3.1-Terminus: 43.5 (#88)
| Benchmark | Claude Sonnet 4 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Longer Query | 1398 | 1426 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference DeepSeek-V3.1-Terminus leads
Claude Sonnet 4: 57.3 (#127), DeepSeek-V3.1-Terminus: 61.3 (#87)
| Benchmark | Claude Sonnet 4 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Text | 1351 | 1420 |
| LMArena Creative Writing | 1345 | 1404 |
| LMArena Multi-Turn | 1376 | 1411 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than DeepSeek-V3.1-Terminus?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 40.6 on the Noometry Index.
Which is cheaper, Claude Sonnet 4 or DeepSeek-V3.1-Terminus?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or DeepSeek-V3.1-Terminus better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 44.0 versus 41.5 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4 does, with 200K tokens against 164K.
How many benchmarks do Claude Sonnet 4 and DeepSeek-V3.1-Terminus share?
16 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.