ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GPT-4ovsGPT-5.4 nano

GPT-5.4 nano leads 3 of 4 shared benchmarks. GPT-5.4 nano is 8.6x cheaper per token. GPT-5.4 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 – 3
GPT-5.4 nano leads
Cheaper per token
GPT-5.4 nano
8.6x cheaper, input + output
Larger context
GPT-5.4 nano
400K tokens
Provider uptime (30d)
94.2446%
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-5.4 nano
OpenAI · released 2026-03-17
textvision
Context
400K
Max out
128K
Input /1M
$0.2
Output /1M
$1.25
Cached /1M
$0.02
Scores
10 · 6 core
Quality

Benchmark matrix

BenchmarkGPT-4oGPT-5.4 nanoΔEdge
Reported by both · 4
GPQA Diamond46% 82.8% -36.8 ptGPT-5.4 nano
FrontierMath Tiers 1-3 v2 (Epoch AI run)0.4% epoch44.9% epoch-44.5 ptGPT-5.4 nano
OTIS Mock AIME 2024-2025 (Epoch AI run)6.4% epoch87.8% epoch-81.4 ptGPT-5.4 nano
SimpleQA Verified26% epoch11.7% epoch+14.3 ptGPT-4o
Only GPT-4o reports · 4
MMLU85.7% not reported
AIME 202511.7% matharenanot reported
AIME 202413.1% not reported
SWE-bench Verified (Epoch AI run)31% epochnot reported
Only GPT-5.4 nano reports · 5
FrontierMath Tier 4 v2 (Epoch AI run)not reported12.2% epoch
OSWorld-Verifiednot reported39%
SWE-Bench Pronot reported52.4%
Terminal-Bench 2.0not reported46.3%
Toolathlonnot reported35.5%
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-5.4 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-5.4 nanoEdge
Context window128K tokens400K tokensGPT-5.4 nano
Max output16K tokens128K tokensGPT-5.4 nano
Input price / 1M$2.5 $0.2 GPT-5.4 nano
Output price / 1M$10 $1.25 GPT-5.4 nano
Cached input / 1M$1.25 $0.02 GPT-5.4 nano
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$12.5$1.45GPT-5.4 nano
Modalitiestext · visiontext · visionTie
Released2024-05-132026-03-17
Cited benchmark scores910
Reliability

OpenAI status

All providers
More matchups

GPT-4o vs …

More matchups

GPT-5.4 nano vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GPT-4o and GPT-5.4 nano on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.