DeepSeek V4 vs GPT-5

Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.

DeepSeek V4

DeepSeek · Mar 2026

The open-weights shock of 2026: ~81% SWE-bench Verified, a 1M context and MIT license at $0.30/$0.50 per million tokens.

GPT-5

OpenAI · Aug 2025

70.7

OpenAI's August 2025 unified flagship that merged the GPT and o-series reasoning lines into one model with selectable effort.

The verdict

DeepSeek V4 wins 1 of the 1 benchmarks these models share, against 0 for GPT-5. On price the gap is dramatic: DeepSeek V4 works out roughly 9.8x cheaper per blended million tokens. DeepSeek V4 also takes 1M of context versus 400K for GPT-5. And DeepSeek V4 is open-weights (MIT), so it can be self-hosted — a structural advantage if data control or vendor independence matters.

Benchmark head-to-head 10

SWE-bench Verified
~81%74.9%
DeepSeek V4GPT-5

Specs & pricing

DeepSeek V4GPT-5
modhub Index70.7
Input price / 1M$0.3$1.25
Output price / 1M$0.5$10
Context window1M400K
Max output64K128K
Open weightsyes (MIT)no
Reasoning modelyesyes
Multimodal inputtexttext, image
Knowledge cutoffDec 2025Sep 2024
ReleasedMar 2026Aug 2025
Example monthly cost*$3.75$27.50

* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.

Frequently asked questions

Which is better, DeepSeek V4 or GPT-5?
DeepSeek V4 wins 1 of the 1 benchmarks these models share, against 0 for GPT-5. On price the gap is dramatic: DeepSeek V4 works out roughly 9.8x cheaper per blended million tokens. DeepSeek V4 also takes 1M of context versus 400K for GPT-5. And DeepSeek V4 is open-weights (MIT), so it can be self-hosted — a structural advantage if data control or vendor independence matters.
Which is cheaper, DeepSeek V4 or GPT-5?
DeepSeek V4 costs $0.3/$0.5 per million input/output tokens, while GPT-5 costs $1.25/$10. For a typical workload of 10M input and 1.5M output tokens per month, that's $3.75 versus $27.50.
Which model is better for coding, DeepSeek V4 or GPT-5?
On SWE-bench Verified — the standard agentic-coding benchmark — DeepSeek V4 scores ~81% versus 74.9% for GPT-5, making DeepSeek V4 the stronger pick for coding agents.

More comparisons