Compare / head-to-head
DeepSeek R1vsDeepSeek V3
DeepSeek R1 leads 7 of 7 shared benchmarks. Both offer a 128K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
7 – 0
DeepSeek R1 leads
Cheaper per token
—
list price, input + output
Larger context
Tie
both 128K tokens
Provider uptime (30d)
100%
DeepSeek
DeepSeek R1
DeepSeek · released 2025-01-20
text
- Context
- 128K
- Max out
- 33K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 8 · 7 core
DeepSeek V3
DeepSeek · released 2024-12-26
text
- Context
- 128K
- Max out
- 8K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 8 · 7 core
Quality
Benchmark matrix
7 shared · 0 only DeepSeek R1 · 0 only DeepSeek V3| Benchmark | DeepSeek R1 | DeepSeek V3 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 7 | ||||
| SWE-bench Verified | 49.2% ↗ | 42% ↗ | +7.2 pt | DeepSeek R1 |
| GPQA Diamond | 71.5% ↗ | 59.1% ↗ | +12.4 pt | DeepSeek R1 |
| MMLU | 90.8% ↗ | 88.5% ↗ | +2.3 pt | DeepSeek R1 |
| MMLU-Pro | 84% ↗ | 75.9% ↗ | +8.1 pt | DeepSeek R1 |
| AIME 2025 | 70% ↗matharena | 25% ↗matharena | +45 pt | DeepSeek R1 |
| LMArena Elo | 1372.6 ↗ | 1332.4 ↗ | +40.2 | DeepSeek R1 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 53.3% ↗epoch | 15.8% ↗epoch | +37.5 pt | DeepSeek R1 |
| Only DeepSeek R1 reports · 0 | ||||
| DeepSeek R1 reports nothing DeepSeek V3 does not. | ||||
| Only DeepSeek V3 reports · 0 | ||||
| DeepSeek V3 reports nothing DeepSeek R1 does not. | ||||
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is DeepSeek R1 minus DeepSeek V3 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | DeepSeek R1 | DeepSeek V3 | Edge |
|---|---|---|---|
| Context window | 128K tokens | 128K tokens | Tie |
| Max output | 33K tokens | 8K tokens | DeepSeek R1 |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text | text | Tie |
| Released | 2025-01-20 | 2024-12-26 | — |
| Cited benchmark scores | 8 | 8 | — |
Reliability
DeepSeek status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
DeepSeek R1 vs …
Models sharing the most benchmarksMore matchups
DeepSeek V3 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek R1 and DeepSeek V3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.