Compare / head-to-head
DeepSeek V4 ProvsGPT-4.1
DeepSeek V4 Pro leads 5 of 5 shared benchmarks. DeepSeek V4 Pro is 7.7x cheaper per token. GPT-4.1 has the larger context window (1.0M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
5 – 0
DeepSeek V4 Pro leads
Cheaper per token
DeepSeek V4 Pro
7.7x cheaper, input + output
Larger context
GPT-4.1
1.0M tokens
Provider uptime (30d)
100% · 94.5578%
DeepSeek · OpenAI
DeepSeek V4 Pro
DeepSeek · released 2026-08-13
text
Quality
Benchmark matrix
5 shared · 6 only DeepSeek V4 Pro · 4 only GPT-4.1| Benchmark | DeepSeek V4 Pro | GPT-4.1 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| GPQA Diamond | 90.9% ↗epoch | 66.3% ↗ | +24.6 pt | DeepSeek V4 Pro |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 45.3% ↗epoch | 6% ↗epoch | +39.3 pt | DeepSeek V4 Pro |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 96.7% ↗epoch | 38.3% ↗epoch | +58.4 pt | DeepSeek V4 Pro |
| SimpleQA Verified | 47% ↗epoch | 31.1% ↗epoch | +15.9 pt | DeepSeek V4 Pro |
| SWE-bench Verified (Epoch AI run) | 77.6% ↗epoch | 48.5% ↗epoch | +29.1 pt | DeepSeek V4 Pro |
| Only DeepSeek V4 Pro reports · 6 | ||||
| AIME 2026 | 96.7% ↗matharena ⚠ | not reported | — | — |
| LMArena Elo | 1450.6 ↗ | not reported | — | — |
| DeepSWE v1.1 | 62.7% ↗ | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 2.4% ↗epoch | not reported | — | — |
| Humanity's Last Exam (with tools) | 60% ↗ | not reported | — | — |
| Terminal-Bench 2.1 | 87.9% ↗ | not reported | — | — |
| Only GPT-4.1 reports · 4 | ||||
| SWE-bench Verified | not reported | 54.6% ↗ | — | — |
| MMLU | not reported | 90.2% ↗ | — | — |
| AIME 2024 | not reported | 48.1% ↗ | — | — |
| Video-MME (long, no subtitles) | not reported | 72% ↗ | — | — |
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 V4 Pro minus GPT-4.1 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 V4 Pro | GPT-4.1 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1.0M tokens | GPT-4.1 |
| Max output | 384K tokens | 33K tokens | DeepSeek V4 Pro |
| Input price / 1M | $0.435 ↗ | $2 ↗ | DeepSeek V4 Pro |
| Output price / 1M | $0.87 ↗ | $8 ↗ | DeepSeek V4 Pro |
| Cached input / 1M | $0.004 ↗ | $0.5 ↗ | DeepSeek V4 Pro |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.31 | $10 | DeepSeek V4 Pro |
| Modalities | text | text · vision | GPT-4.1 |
| Released | 2026-08-13 | 2025-04-14 | — |
| Cited benchmark scores | 11 | 10 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
DeepSeek V4 Pro vs …
Models sharing the most benchmarksMore matchups
GPT-4.1 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V4 Pro and GPT-4.1 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.