Compare / head-to-head
Claude 3.5 SonnetvsDeepSeek V4.1 Flash
DeepSeek V4.1 Flash leads 1 of 1 shared benchmark. DeepSeek V4.1 Flash is 42.9x cheaper per token. DeepSeek V4.1 Flash has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 1
DeepSeek V4.1 Flash leads
Cheaper per token
DeepSeek V4.1 Flash
42.9x cheaper, input + output
Larger context
DeepSeek V4.1 Flash
1M tokens
Provider uptime (30d)
100% · 100%
Anthropic · DeepSeek
Claude 3.5 Sonnet
Anthropic · released 2024-10-22
textvision
DeepSeek V4.1 Flash
DeepSeek · released 2026-09-10
textvision
Quality
Benchmark matrix
1 shared · 3 only Claude 3.5 Sonnet · 2 only DeepSeek V4.1 Flash| Benchmark | Claude 3.5 Sonnet | DeepSeek V4.1 Flash | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| GPQA Diamond | 55.3% ↗epoch | 90.9% ↗ | -35.6 pt | DeepSeek V4.1 Flash |
| Only Claude 3.5 Sonnet reports · 3 | ||||
| SWE-bench Verified | 49% ↗ | not reported | — | — |
| AIME 2025 | 3.3% ↗matharena | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 8.5% ↗epoch | not reported | — | — |
| Only DeepSeek V4.1 Flash reports · 2 | ||||
| DeepSWE v1.1 | not reported | 74.2% ↗ | — | — |
| Terminal-Bench 2.1 | not reported | 90.6% ↗ | — | — |
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 Claude 3.5 Sonnet minus DeepSeek V4.1 Flash 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 | Claude 3.5 Sonnet | DeepSeek V4.1 Flash | Edge |
|---|---|---|---|
| Context window | 200K tokens | 1M tokens | DeepSeek V4.1 Flash |
| Max output | 8K tokens | 384K tokens | DeepSeek V4.1 Flash |
| Input price / 1M | $3 ↗ | $0.14 ↗ | DeepSeek V4.1 Flash |
| Output price / 1M | $15 ↗ | $0.28 ↗ | DeepSeek V4.1 Flash |
| Cached input / 1M | $0.3 ↗ | $0.003 ↗ | DeepSeek V4.1 Flash |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $18 | $0.42 | DeepSeek V4.1 Flash |
| Modalities | text · vision | text · vision | Tie |
| Released | 2024-10-22 | 2026-09-10 | — |
| Cited benchmark scores | 4 | 3 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude 3.5 Sonnet vs …
Models sharing the most benchmarksMore matchups
DeepSeek V4.1 Flash vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude 3.5 Sonnet and DeepSeek V4.1 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.