ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

DeepSeek V3vsGPT-5 nano

GPT-5 nano leads 4 of 4 shared benchmarks. GPT-5 nano has the larger context window (400K tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 4
GPT-5 nano leads
Cheaper per token
list price, input + output
Larger context
GPT-5 nano
400K tokens
Provider uptime (30d)
100% · 94.2446%
DeepSeek · OpenAI
DeepSeek V3
DeepSeek · released 2024-12-26
text
Context
128K
Max out
8K
Input /1M
Output /1M
Cached /1M
Scores
8 · 7 core
GPT-5 nano
OpenAI · released 2025-08-07
textvision
Context
400K
Max out
128K
Input /1M
$0.05
Output /1M
$0.4
Cached /1M
$0.005
Scores
7 · 7 core
Quality

Benchmark matrix

BenchmarkDeepSeek V3GPT-5 nanoΔEdge
Reported by both · 4
SWE-bench Verified42% 54.7% -12.7 ptGPT-5 nano
GPQA Diamond59.1% 69.4% epoch-10.3 ptGPT-5 nano
AIME 202525% matharena85% matharena-60 ptGPT-5 nano
OTIS Mock AIME 2024-2025 (Epoch AI run)15.8% epoch81.1% epoch-65.3 ptGPT-5 nano
Only DeepSeek V3 reports · 3
MMLU88.5% not reported
MMLU-Pro75.9% not reported
LMArena Elo1332.4 not reported
Only GPT-5 nano reports · 3
FrontierMath Tier 4 v2 (Epoch AI run)not reported2.4% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported20% epoch
SimpleQA Verifiednot reported11.7% epoch
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 V3 minus GPT-5 nano 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

SpecDeepSeek V3GPT-5 nanoEdge
Context window128K tokens400K tokensGPT-5 nano
Max output8K tokens128K tokensGPT-5 nano
Input price / 1M$0.05
Output price / 1M$0.4
Cached input / 1M$0.005
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$0.45
Modalitiestexttext · visionGPT-5 nano
Released2024-12-262025-08-07
Cited benchmark scores87
Reliability

Provider status

All providers
More matchups

DeepSeek V3 vs …

More matchups

GPT-5 nano vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run DeepSeek V3 and GPT-5 nano on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.