AI lab · 12 models tracked
DeepSeek models
Every DeepSeek model released in the last 18 months, with release dates, context windows, API prices and benchmark scores. Newest: DeepSeek V4.1 Flash 1017, 3d ago.
- Models · 30 days
- 1 of 12
- Latest release
- 3d ago
- Cheapest input / 1M
- $0.056 DeepSeek V4.1 Flash
- Largest context
- 1M DeepSeek V4.1 Flash 1017
Release history
Timeline
DeepSeek ships a new model about every 46 days. Each dot is a release; click one to open it.
Lineup
All DeepSeek models
Benchmarks
DeepSeek's best scores
The top DeepSeek model on each benchmark, and where it ranks among all 222 tracked models.
| Benchmark | Best DeepSeek model | Score | Overall rank |
|---|---|---|---|
| FrontierCodeSoftware engineering | DeepSeek V4.1 Flash 1017 | 43.9% | #16of 41 |
| SWE-bench VerifiedSoftware engineering | DeepSeek V4 Pro 0813 | 77.6% | #5of 26 |
| Terminal-BenchSoftware engineering | DeepSeek V3.2 | 39.6% | #23of 40 |
| SciCodeSoftware engineering | DeepSeek V4.1 Flash 1017 | 51.8% | #39of 93 |
| Aider PolyglotSoftware engineering | DeepSeek V3.2 | 74.2% | #3of 11 |
| WeirdML v3Software engineering | DeepSeek V4.1 Flash 1017 | 5.9% | #18of 22 |
| METR time horizonSoftware engineering | R1 0528 | 31 min | #13of 13 |
| APEX-AgentsAgents & computer use | DeepSeek V4 Pro 0813 | 47.3% | #30of 51 |
| Vending-Bench 2Agents & computer use | DeepSeek V4 Pro 0813 | $3,285 | #41of 61 |
| Lech Mazur WritingWriting & content | R1 0528 | 8.30/10 | #7of 13 |
| Fiction.LiveBenchWriting & content | DeepSeek V3.2 | 83.3% | #4of 15 |
| DeepResearch BenchWriting & content | R1 0528 | 35.1% | #19of 20 |
| GDP.pdfWriting & content | DeepSeek V4.1 Flash 1017 | 19.8% | #22of 38 |
| SimpleQA VerifiedWriting & content | DeepSeek V4 Pro 0813 | 52.9% | #22of 66 |
| WebDev ArenaDesign & visual | DeepSeek V4.1 Flash 1017 | 1614 | #18of 88 |
| Furniture AssemblyDesign & visual | DeepSeek V4.1 Flash 1017 | 34.2% | #20of 34 |
| GPQA DiamondReasoning & knowledge | DeepSeek V4 Pro 0813 | 91.7% | #22of 92 |
| ARC-AGI-2Reasoning & knowledge | DeepSeek V4.1 Flash 1017 | 72.9% | #19of 63 |
| ARC-AGI-1Reasoning & knowledge | DeepSeek V4.1 Flash 1017 | 94.5% | #16of 63 |
| SimpleBenchReasoning & knowledge | DeepSeek V4 Flash 0731 | 61.1% | #18of 43 |
| CritPtReasoning & knowledge | DeepSeek V4 Pro 0813 | 18.0% | #29of 96 |
| Chess PuzzlesReasoning & knowledge | DeepSeek V4.1 Flash 1017 | 48.0% | #17of 70 |
| LMCAReasoning & knowledge | DeepSeek V4.1 Flash 1017 | 47.0% | #32of 96 |
| FrontierMathMaths | DeepSeek V4.1 Flash 1017 | 67.4% | #29of 72 |
| FrontierMath Tier 4Maths | DeepSeek V4.1 Flash 1017 | 26.8% | #32of 62 |
| ProofBenchMaths | DeepSeek V4 Flash 0731 | 56.0% | #24of 70 |
| OTIS Mock AIMEMaths | DeepSeek V4 Pro 0813 | 98.6% | #18of 90 |
Directory