Model comparison
Claude Opus 5 vs DeepSeek V4.1 Flash
Claude Opus 5 is the stronger model overall, scoring 67.8 to 52.8 on the Noometry Index. DeepSeek V4.1 Flash costs 38× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Last verified . 36 shared benchmarks.
DeepSeekSummary
- They share 36 benchmarks with published results for both. Claude Opus 5 scores higher in 10 categories and DeepSeek V4.1 Flash in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5 leads 77.2 to 50.2.
- The biggest single-benchmark swing is FrontierMath Tier 4: 73.2% for Claude Opus 5 and 26.8% for DeepSeek V4.1 Flash.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $5 / $25 for Claude Opus 5.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 5 | DeepSeek V4.1 Flash | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 67.8 | 52.8 |
| Released | 2026-07-24 | 2026-09-09 |
| Weights | Proprietary | Open |
| Context window | 1M | 1M |
| Max output | 128K | 393K |
| Input $ / M tokens | $5 | $0.15 |
| Output $ / M tokens | $25 | $0.60 |
| Results tracked | 57 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.5 (#5), DeepSeek V4.1 Flash: 52.9 (#32)
| Benchmark | Claude Opus 5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena WebDev | 1691 | 1619 |
| SciCode | 56.4% | 51.9% |
| LMArena Coding | 1534 | 1506 |
| ALE-Bench | 2,165 | 1,092 |
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| CursorBench | 46.6% | — |
| FrontierSWE | 52% | — |
| WeirdML | 91.8% | — |
Agentic & Tool Use Claude Opus 5 leads
Claude Opus 5: 55.6 (#1), DeepSeek V4.1 Flash: 31.2 (#69)
| Benchmark | Claude Opus 5 | DeepSeek V4.1 Flash |
|---|---|---|
| APEX-Agents | 65.8% | 39.5% |
| GDP.pdf | 24% | 19.8% |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| Vending-Bench 2 | 11,182 | — |
Reasoning Claude Opus 5 leads
Claude Opus 5: 77.2 (#4), DeepSeek V4.1 Flash: 50.2 (#36)
| Benchmark | Claude Opus 5 | DeepSeek V4.1 Flash |
|---|---|---|
| NYT Connections (extended) | 94.3% | 89.6% |
| CritPt | 29.1% | 14.3% |
| LMArena Hard Prompts | 1526 | 1483 |
| Mystery Game Puzzles | 59% | 43% |
| DTBench | 97.9% | 89.9% |
| LMCA | 64.5% | 47% |
| Epoch Capabilities Index | 162.78 | 154.9 |
| ARC-AGI-2 | 90.4% | — |
| SimpleBench | 80.6% | — |
| ARC-AGI-1 | 97.5% | — |
| Chess Puzzles | 42% | — |
| EBR-Bench | 45.7% | — |
| Surface Evolver Bench | — | 46.3% |
| Bench to the Future 3 | 0.12 | — |
Math Claude Opus 5 leads
Claude Opus 5: 86.2 (#8), DeepSeek V4.1 Flash: 66.7 (#25)
| Benchmark | Claude Opus 5 | DeepSeek V4.1 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.6% | 67.4% |
| FrontierMath Tier 4 | 73.2% | 26.8% |
| OTIS Mock AIME 2024-2025 | 98.9% | 98.3% |
| ProofBench | 99% | 54% |
| LMArena Math | 1531 | 1477 |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#9), DeepSeek V4.1 Flash: 57.9 (#38)
| Benchmark | Claude Opus 5 | DeepSeek V4.1 Flash |
|---|---|---|
| GPQA Diamond | 93.9% | 89.8% |
| LMArena Expert | 1557 | 1506 |
| SimpleQA Verified | 59.9% | — |
Multimodal Claude Opus 5 leads
Claude Opus 5: 50.8 (#8), DeepSeek V4.1 Flash: 39.1 (#61)
| Benchmark | Claude Opus 5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Vision | 1319 | 1277 |
| Furniture Assembly | 60.8% | 34.2% |
| Blueprint-Bench 2 | 30.4% | — |
| LMArena Document | 1516 | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#4), DeepSeek V4.1 Flash: 55.0 (#35)
| Benchmark | Claude Opus 5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Non-English | 1501 | 1448 |
| LMArena Chinese | 1574 | 1497 |
| LMArena French | 1519 | 1452 |
| LMArena German | 1524 | 1484 |
| LMArena Japanese | 1516 | 1412 |
| LMArena Korean | 1521 | 1452 |
| LMArena Russian | 1507 | 1471 |
| LMArena Spanish | 1519 | 1459 |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.2 (#7), DeepSeek V4.1 Flash: 77.3 (#26)
| Benchmark | Claude Opus 5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Instruction Following | 1517 | 1474 |
Long Context Claude Opus 5 leads
Claude Opus 5: 46.5 (#21), DeepSeek V4.1 Flash: 45.2 (#47)
| Benchmark | Claude Opus 5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Longer Query | 1515 | 1475 |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.2 (#1), DeepSeek V4.1 Flash: 65.4 (#48)
| Benchmark | Claude Opus 5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Text | 1507 | 1462 |
| LMArena Creative Writing | 1491 | 1435 |
| EQ-Bench Creative Writing | 2133 | 1540 |
| LMArena Multi-Turn | 1499 | 1457 |
| EQ-Bench 4 | 1385 | — |
Frequently asked questions
Is Claude Opus 5 better than DeepSeek V4.1 Flash?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 52.8 on the Noometry Index. DeepSeek V4.1 Flash costs 38× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 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 Opus 5 lists at $5 and $25.
Is Claude Opus 5 or DeepSeek V4.1 Flash better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 52.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Opus 5 and DeepSeek V4.1 Flash share?
36 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and DeepSeek V4.1 Flash has 37.