Model comparison
Claude Opus 4.8 vs DeepSeek V4.1 Flash
Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 50.3 on the Noometry Index. DeepSeek V4.1 Flash costs 38× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
DeepSeekSummary
- They share 25 benchmarks with published results for both. Claude Opus 4.8 scores higher in 7 categories and DeepSeek V4.1 Flash in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.8 leads 78.2 to 48.4.
- The biggest single-benchmark swing is Surface Evolver Bench: 87.5% for Claude Opus 4.8 and 46.3% 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 4.8.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.8 | DeepSeek V4.1 Flash | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 60.7 | 50.3 |
| Released | 2026-05-28 | 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 | 65 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.8 leads
Claude Opus 4.8: 60.2 (#9), DeepSeek V4.1 Flash: 52.8 (#29)
| Benchmark | Claude Opus 4.8 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena WebDev | 1556 | 1620 |
| SciCode | 53.5% | 51.9% |
| LMArena Coding | 1491 | 1511 |
| ALE-Bench | 1,564 | 1,092 |
| DeepSWE | 59% | — |
| FrontierCode | 46.5% | — |
| GSO | 47.1% | — |
| WeirdML | 82.9% | — |
Agentic & Tool Use Not comparable
Claude Opus 4.8: 47.6 (#10), DeepSeek V4.1 Flash: —
| Benchmark | Claude Opus 4.8 | DeepSeek V4.1 Flash |
|---|---|---|
| APEX-Agents | 48.9% | — |
| OSWorld 2.0 | 20.6% | — |
| Remote Labor Index | 8.3% | — |
| τ²-bench Banking | 39.7% | — |
| DeepResearch Bench | 50.2% | — |
| PostTrainBench | 33.8% | — |
| GBAEval | 70.9% | — |
| GDP.pdf | 24% | — |
| LMArena Search | 1204 | — |
| Vending-Bench 2 | 5,787 | — |
Reasoning Claude Opus 4.8 leads
Claude Opus 4.8: 64.6 (#14), DeepSeek V4.1 Flash: 46.2 (#39)
| Benchmark | Claude Opus 4.8 | DeepSeek V4.1 Flash |
|---|---|---|
| NYT Connections (extended) | 91.1% | 89.6% |
| CritPt | 20.9% | 14.3% |
| LMArena Hard Prompts | 1481 | 1485 |
| DTBench | 94.9% | 89.9% |
| LMCA | 57.5% | 47% |
| Surface Evolver Bench | 87.5% | 46.3% |
| Epoch Capabilities Index | 158.3 | 155.01 |
| ARC-AGI-2 | 72.1% | — |
| SimpleBench | 64.8% | — |
| Kagi LLM Benchmark | 88.8% | — |
| ARC-AGI-1 | 92.5% | — |
| Chess Puzzles | 34% | — |
| EnigmaEval | 23.5% | — |
| EBR-Bench | 28.6% | — |
| Mystery Game Puzzles | 36% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 59.9 | — |
Math Claude Opus 4.8 leads
Claude Opus 4.8: 78.2 (#11), DeepSeek V4.1 Flash: 48.4 (#52)
| Benchmark | Claude Opus 4.8 | DeepSeek V4.1 Flash |
|---|---|---|
| ProofBench | 69% | 54% |
| LMArena Math | 1487 | 1493 |
| FrontierMath (Tiers 1-3) | 80% | — |
| FrontierMath Tier 4 | 56.1% | — |
| MathArena Final-Answer Competitions | 91.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| FrontierMath (Feb 2025 set) | 47.2% | — |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Claude Opus 4.8 leads
Claude Opus 4.8: 61.3 (#26), DeepSeek V4.1 Flash: 41.6 (#97)
| Benchmark | Claude Opus 4.8 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Expert | 1501 | 1505 |
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 53% | — |
Multimodal Not comparable
Claude Opus 4.8: 43.2 (#20), DeepSeek V4.1 Flash: —
| Benchmark | Claude Opus 4.8 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Vision | 1295 | — |
| Blueprint-Bench 2 | 14.5% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1475 | — |
Multilingual Too close to call
Claude Opus 4.8: 55.4 (#31), DeepSeek V4.1 Flash: 55.5 (#29)
| Benchmark | Claude Opus 4.8 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Non-English | 1450 | 1452 |
| LMArena Chinese | 1509 | 1506 |
| LMArena French | 1482 | 1448 |
| LMArena Russian | 1476 | 1473 |
| LMArena Spanish | 1470 | 1499 |
| LMArena German | 1470 | — |
| LMArena Japanese | 1440 | — |
| LMArena Korean | 1432 | — |
Instruction Following Too close to call
Claude Opus 4.8: 77.6 (#22), DeepSeek V4.1 Flash: 77.6 (#24)
| Benchmark | Claude Opus 4.8 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Instruction Following | 1476 | 1475 |
Long Context Too close to call
Claude Opus 4.8: 45.4 (#37), DeepSeek V4.1 Flash: 45.2 (#46)
| Benchmark | Claude Opus 4.8 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Longer Query | 1482 | 1476 |
Writing & Preference Claude Opus 4.8 leads
Claude Opus 4.8: 72.1 (#17), DeepSeek V4.1 Flash: 65.8 (#43)
| Benchmark | Claude Opus 4.8 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Text | 1460 | 1465 |
| LMArena Creative Writing | 1453 | 1436 |
| EQ-Bench Creative Writing | 1840 | 1540 |
| LMArena Multi-Turn | 1476 | 1460 |
| EQ-Bench 4 | 1281 | — |
Frequently asked questions
Is Claude Opus 4.8 better than DeepSeek V4.1 Flash?
Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 50.3 on the Noometry Index. DeepSeek V4.1 Flash costs 38× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4.8 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 4.8 lists at $5 and $25.
Is Claude Opus 4.8 or DeepSeek V4.1 Flash better for coding?
Claude Opus 4.8 scores higher on coding benchmarks: 60.2 versus 52.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Opus 4.8 and DeepSeek V4.1 Flash share?
25 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and DeepSeek V4.1 Flash has 25.