Model comparison
Claude Sonnet 5 vs DeepSeek V4.1 Flash
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 52.8 on the Noometry Index. DeepSeek V4.1 Flash costs 15× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 35 shared benchmarks.
DeepSeekSummary
- They share 35 benchmarks with published results for both. Claude Sonnet 5 scores higher in 4 categories and DeepSeek V4.1 Flash in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Sonnet 5 leads 42.8 to 31.2.
- The biggest single-benchmark swing is ProofBench: 77% for Claude Sonnet 5 and 54% for DeepSeek V4.1 Flash.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | DeepSeek V4.1 Flash | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 54.6 | 52.8 |
| Released | 2026-06-29 | 2026-09-09 |
| Weights | Proprietary | Open |
| Context window | 1M | 1M |
| Max output | 128K | 393K |
| Input $ / M tokens | $2 | $0.15 |
| Output $ / M tokens | $10 | $0.60 |
| Results tracked | 51 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), DeepSeek V4.1 Flash: 52.9 (#32)
| Benchmark | Claude Sonnet 5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena WebDev | 1541 | 1619 |
| SciCode | 54.3% | 51.9% |
| LMArena Coding | 1483 | 1506 |
| ALE-Bench | 1,463 | 1,092 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.8 (#18), DeepSeek V4.1 Flash: 31.2 (#69)
| Benchmark | Claude Sonnet 5 | DeepSeek V4.1 Flash |
|---|---|---|
| APEX-Agents | 54.5% | 39.5% |
| GBAEval | 65.3% | — |
| GDP.pdf | — | 19.8% |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning DeepSeek V4.1 Flash leads
Claude Sonnet 5: 49.1 (#39), DeepSeek V4.1 Flash: 50.2 (#36)
| Benchmark | Claude Sonnet 5 | DeepSeek V4.1 Flash |
|---|---|---|
| NYT Connections (extended) | 75.1% | 89.6% |
| CritPt | 16.9% | 14.3% |
| LMArena Hard Prompts | 1461 | 1483 |
| Mystery Game Puzzles | 35% | 43% |
| DTBench | 92.5% | 89.9% |
| LMCA | 50% | 47% |
| Surface Evolver Bench | 60% | 46.3% |
| Epoch Capabilities Index | 156.21 | 154.9 |
| SimpleBench | 60.6% | — |
| Chess Puzzles | 35% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |
Math Too close to call
Claude Sonnet 5: 66.2 (#27), DeepSeek V4.1 Flash: 66.7 (#25)
| Benchmark | Claude Sonnet 5 | DeepSeek V4.1 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 67.4% |
| FrontierMath Tier 4 | 29.3% | 26.8% |
| OTIS Mock AIME 2024-2025 | 94.7% | 98.3% |
| ProofBench | 77% | 54% |
| LMArena Math | 1467 | 1477 |
Knowledge DeepSeek V4.1 Flash leads
Claude Sonnet 5: 55.6 (#47), DeepSeek V4.1 Flash: 57.9 (#38)
| Benchmark | Claude Sonnet 5 | DeepSeek V4.1 Flash |
|---|---|---|
| GPQA Diamond | 90.5% | 89.8% |
| LMArena Expert | 1490 | 1506 |
| SimpleQA Verified | 33.7% | — |
Multimodal Claude Sonnet 5 leads
Claude Sonnet 5: 42.4 (#31), DeepSeek V4.1 Flash: 39.1 (#61)
| Benchmark | Claude Sonnet 5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Vision | 1274 | 1277 |
| Blueprint-Bench 2 | 24.9% | — |
| Furniture Assembly | — | 34.2% |
| LMArena Document | 1466 | — |
Multilingual DeepSeek V4.1 Flash leads
Claude Sonnet 5: 53.8 (#55), DeepSeek V4.1 Flash: 55.0 (#35)
| Benchmark | Claude Sonnet 5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Non-English | 1431 | 1448 |
| LMArena Chinese | 1477 | 1497 |
| LMArena French | 1460 | 1452 |
| LMArena German | 1440 | 1484 |
| LMArena Japanese | 1422 | 1412 |
| LMArena Korean | 1411 | 1452 |
| LMArena Russian | 1451 | 1471 |
| LMArena Spanish | 1437 | 1459 |
Instruction Following DeepSeek V4.1 Flash leads
Claude Sonnet 5: 76.3 (#41), DeepSeek V4.1 Flash: 77.3 (#26)
| Benchmark | Claude Sonnet 5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Instruction Following | 1452 | 1474 |
Long Context Too close to call
Claude Sonnet 5: 44.8 (#55), DeepSeek V4.1 Flash: 45.2 (#47)
| Benchmark | Claude Sonnet 5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Longer Query | 1463 | 1475 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), DeepSeek V4.1 Flash: 65.4 (#48)
| Benchmark | Claude Sonnet 5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Text | 1442 | 1462 |
| LMArena Creative Writing | 1416 | 1435 |
| EQ-Bench Creative Writing | 1794 | 1540 |
| LMArena Multi-Turn | 1454 | 1457 |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than DeepSeek V4.1 Flash?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 52.8 on the Noometry Index. DeepSeek V4.1 Flash costs 15× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5 or DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or DeepSeek V4.1 Flash better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 52.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Sonnet 5 and DeepSeek V4.1 Flash share?
35 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and DeepSeek V4.1 Flash has 37.