Model comparison
Claude Sonnet 4.6 vs DeepSeek V4 Flash
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 50.3 on the Noometry Index.
Last verified . 36 shared benchmarks.
DeepSeekSummary
- They share 36 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 4 categories and DeepSeek V4 Flash in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 46.1.
- The biggest single-benchmark swing is Chess Puzzles: 13% for Claude Sonnet 4.6 and 33% for DeepSeek V4 Flash.
- DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.6 | DeepSeek V4 Flash | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 50.3 | 53.6 |
| Released | 2026-02-17 | 2026-04-24 |
| Weights | Proprietary | Open |
| Context window | 1M | 1M |
| Max output | 128K | 393K |
| Input $ / M tokens | $3 | $0.15 |
| Output $ / M tokens | $15 | $0.60 |
| Results tracked | 57 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
Claude Sonnet 4.6: 46.3 (#67), DeepSeek V4 Flash: 47.9 (#59)
| Benchmark | Claude Sonnet 4.6 | DeepSeek V4 Flash |
|---|---|---|
| FrontierCode | 24.3% | 18.8% |
| LMArena WebDev | 1522 | 1582 |
| SciCode | 46.8% | 49.9% |
| WeirdML | 66.1% | 63% |
| LMArena Coding | 1504 | 1457 |
| ALE-Bench | 1,327 | 1,306 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4.6: 39.1 (#28), DeepSeek V4 Flash: —
| Benchmark | Claude Sonnet 4.6 | DeepSeek V4 Flash |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |
Reasoning DeepSeek V4 Flash leads
Claude Sonnet 4.6: 46.1 (#45), DeepSeek V4 Flash: 53.7 (#30)
| Benchmark | Claude Sonnet 4.6 | DeepSeek V4 Flash |
|---|---|---|
| ARC-AGI-2 | 60.4% | 61.4% |
| NYT Connections (extended) | 80.9% | 89.6% |
| ARC-AGI-1 | 86.5% | 89% |
| CritPt | 3.1% | 16.6% |
| Chess Puzzles | 13% | 33% |
| LMArena Hard Prompts | 1484 | 1444 |
| Mystery Game Puzzles | 16% | 34% |
| DTBench | 89.9% | 90.9% |
| LMCA | 46.5% | 41.7% |
| Epoch Capabilities Index | 152.24 | 154.49 |
| SimpleBench | — | 61.1% |
| Kagi LLM Benchmark | — | 52.2% |
| Thematic Generalization | 76.3% | — |
| ForecastBench | 62 | — |
Math DeepSeek V4 Flash leads
Claude Sonnet 4.6: 52.9 (#49), DeepSeek V4 Flash: 60.3 (#37)
| Benchmark | Claude Sonnet 4.6 | DeepSeek V4 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 94.4% |
| ProofBench | 45% | 56% |
| LMArena Math | 1462 | 1427 |
| FrontierMath (Tiers 1-3) | — | 57.5% |
| FrontierMath Tier 4 | — | 24.4% |
| MathArena Final-Answer Competitions | — | 76.5% |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge DeepSeek V4 Flash leads
Claude Sonnet 4.6: 51.7 (#65), DeepSeek V4 Flash: 55.4 (#48)
| Benchmark | Claude Sonnet 4.6 | DeepSeek V4 Flash |
|---|---|---|
| GPQA Diamond | 87.4% | 91% |
| SimpleQA Verified | 35.5% | 33.6% |
| LMArena Expert | 1500 | 1441 |
| Vectara Hallucination Rate | 10.6% | — |
Multimodal Not comparable
Claude Sonnet 4.6: 38.0 (#68), DeepSeek V4 Flash: —
| Benchmark | Claude Sonnet 4.6 | DeepSeek V4 Flash |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |
Multilingual Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 54.4 (#41), DeepSeek V4 Flash: 53.0 (#72)
| Benchmark | Claude Sonnet 4.6 | DeepSeek V4 Flash |
|---|---|---|
| LMArena Non-English | 1440 | 1420 |
| LMArena Chinese | 1491 | 1468 |
| LMArena French | 1465 | 1439 |
| LMArena German | 1428 | 1418 |
| LMArena Japanese | 1420 | 1406 |
| LMArena Korean | 1411 | 1384 |
| LMArena Russian | 1440 | 1428 |
| LMArena Spanish | 1464 | 1436 |
Instruction Following Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 77.4 (#25), DeepSeek V4 Flash: 74.9 (#81)
| Benchmark | Claude Sonnet 4.6 | DeepSeek V4 Flash |
|---|---|---|
| LMArena Instruction Following | 1475 | 1421 |
Long Context Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 45.3 (#44), DeepSeek V4 Flash: 43.8 (#85)
| Benchmark | Claude Sonnet 4.6 | DeepSeek V4 Flash |
|---|---|---|
| LMArena Longer Query | 1479 | 1434 |
Writing & Preference Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 70.2 (#22), DeepSeek V4 Flash: 63.8 (#61)
| Benchmark | Claude Sonnet 4.6 | DeepSeek V4 Flash |
|---|---|---|
| LMArena Text | 1458 | 1432 |
| LMArena Creative Writing | 1435 | 1403 |
| EQ-Bench Creative Writing | 1810 | 1559 |
| LMArena Multi-Turn | 1464 | 1449 |
| EQ-Bench 4 | 1207 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than DeepSeek V4 Flash?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 50.3 on the Noometry Index.
Which is cheaper, Claude Sonnet 4.6 or DeepSeek V4 Flash?
DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or DeepSeek V4 Flash better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 46.3 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Sonnet 4.6 and DeepSeek V4 Flash share?
36 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and DeepSeek V4 Flash has 41.