ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GPT-4ovsGPT-5 nano

GPT-5 nano leads 4 of 5 shared benchmarks. GPT-5 nano is 27.8x cheaper per token. 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
1 – 4
GPT-5 nano leads
Cheaper per token
GPT-5 nano
27.8x cheaper, input + output
Larger context
GPT-5 nano
400K tokens
Provider uptime (30d)
95.5182%
OpenAI
GPT-4o
OpenAI · released 2024-05-13
textvision
Context
128K
Max out
16K
Input /1M
$2.5
Output /1M
$10
Cached /1M
$1.25
Scores
9 · 8 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

BenchmarkGPT-4oGPT-5 nanoΔEdge
Reported by both · 5
GPQA Diamond46% 69.4% epoch-23.4 ptGPT-5 nano
AIME 202511.7% matharena85% matharena-73.3 ptGPT-5 nano
FrontierMath Tiers 1-3 v2 (Epoch AI run)0.4% epoch20% epoch-19.6 ptGPT-5 nano
OTIS Mock AIME 2024-2025 (Epoch AI run)6.4% epoch81.1% epoch-74.7 ptGPT-5 nano
SimpleQA Verified26% epoch11.7% epoch+14.3 ptGPT-4o
Only GPT-4o reports · 3
MMLU85.7% not reported
AIME 202413.1% not reported
SWE-bench Verified (Epoch AI run)31% epochnot reported
Only GPT-5 nano reports · 2
SWE-bench Verifiednot reported54.7%
FrontierMath Tier 4 v2 (Epoch AI run)not reported2.4% 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 GPT-4o 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

SpecGPT-4oGPT-5 nanoEdge
Context window128K tokens400K tokensGPT-5 nano
Max output16K tokens128K tokensGPT-5 nano
Input price / 1M$2.5 $0.05 GPT-5 nano
Output price / 1M$10 $0.4 GPT-5 nano
Cached input / 1M$1.25 $0.005 GPT-5 nano
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$12.5$0.45GPT-5 nano
Modalitiestext · visiontext · visionTie
Released2024-05-132025-08-07
Cited benchmark scores97
Reliability

OpenAI status

All providers
More matchups

GPT-4o vs …

More matchups

GPT-5 nano vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GPT-4o and GPT-5 nano on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.