Model comparison
Claude 3.7 Sonnet vs DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 39.5 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeekSummary
- They share 22 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 2 categories and DeepSeek V4.1 Flash in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 50.2 to 18.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 98.3% for DeepSeek V4.1 Flash.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | DeepSeek V4.1 Flash | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 39.5 | 52.8 |
| Released | 2025-02-24 | 2026-09-09 |
| Weights | Proprietary | Open |
| Context window | — | 1M |
| Max output | — | 393K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 58 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
Claude 3.7 Sonnet: 40.6 (#136), DeepSeek V4.1 Flash: 52.9 (#32)
| Benchmark | Claude 3.7 Sonnet | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Coding | 1361 | 1506 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1619 |
| SciCode | — | 51.9% |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 1,092 |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 34.1 (#50), DeepSeek V4.1 Flash: 31.2 (#69)
| Benchmark | Claude 3.7 Sonnet | DeepSeek V4.1 Flash |
|---|---|---|
| APEX-Agents | — | 39.5% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| GDP.pdf | — | 19.8% |
| METR Time Horizons | 60% | — |
Reasoning DeepSeek V4.1 Flash leads
Claude 3.7 Sonnet: 18.6 (#277), DeepSeek V4.1 Flash: 50.2 (#36)
| Benchmark | Claude 3.7 Sonnet | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1483 |
| Epoch Capabilities Index | 141.16 | 154.9 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| NYT Connections (extended) | — | 89.6% |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 14.3% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 43% |
| DTBench | — | 89.9% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 47% |
| Surface Evolver Bench | — | 46.3% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math DeepSeek V4.1 Flash leads
Claude 3.7 Sonnet: 37.5 (#153), DeepSeek V4.1 Flash: 66.7 (#25)
| Benchmark | Claude 3.7 Sonnet | DeepSeek V4.1 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 98.3% |
| LMArena Math | 1337 | 1477 |
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 26.8% |
| ProofBench | — | 54% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge DeepSeek V4.1 Flash leads
Claude 3.7 Sonnet: 39.8 (#130), DeepSeek V4.1 Flash: 57.9 (#38)
| Benchmark | Claude 3.7 Sonnet | DeepSeek V4.1 Flash |
|---|---|---|
| GPQA Diamond | 79.7% | 89.8% |
| LMArena Expert | 1321 | 1506 |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal DeepSeek V4.1 Flash leads
Claude 3.7 Sonnet: 33.7 (#95), DeepSeek V4.1 Flash: 39.1 (#61)
| Benchmark | Claude 3.7 Sonnet | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Vision | 1169 | 1277 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| Furniture Assembly | — | 34.2% |
| SpatialViz-Bench | 33.9% | — |
Multilingual DeepSeek V4.1 Flash leads
Claude 3.7 Sonnet: 44.1 (#179), DeepSeek V4.1 Flash: 55.0 (#35)
| Benchmark | Claude 3.7 Sonnet | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Non-English | 1296 | 1448 |
| LMArena Chinese | 1299 | 1497 |
| LMArena French | 1303 | 1452 |
| LMArena German | 1301 | 1484 |
| LMArena Japanese | 1267 | 1412 |
| LMArena Korean | 1249 | 1452 |
| LMArena Russian | 1311 | 1471 |
| LMArena Spanish | 1298 | 1459 |
Instruction Following DeepSeek V4.1 Flash leads
Claude 3.7 Sonnet: 72.9 (#125), DeepSeek V4.1 Flash: 77.3 (#26)
| Benchmark | Claude 3.7 Sonnet | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Instruction Following | 1352 | 1474 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), DeepSeek V4.1 Flash: 45.2 (#47)
| Benchmark | Claude 3.7 Sonnet | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Longer Query | 1373 | 1475 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference DeepSeek V4.1 Flash leads
Claude 3.7 Sonnet: 54.4 (#150), DeepSeek V4.1 Flash: 65.4 (#48)
| Benchmark | Claude 3.7 Sonnet | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Text | 1314 | 1462 |
| LMArena Creative Writing | 1332 | 1435 |
| EQ-Bench Creative Writing | 1412 | 1540 |
| LMArena Multi-Turn | 1339 | 1457 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or DeepSeek V4.1 Flash better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and DeepSeek V4.1 Flash share?
22 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and DeepSeek V4.1 Flash has 37.