ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GPT-5 nanovso3

o3 leads 6 of 6 shared benchmarks. GPT-5 nano is 22.2x 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
0 – 6
o3 leads
Cheaper per token
GPT-5 nano
22.2x cheaper, input + output
Larger context
GPT-5 nano
400K tokens
Provider uptime (30d)
94.2446%
OpenAI
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
o3
OpenAI · released 2025-04-16
textvision
Context
200K
Max out
100K
Input /1M
$2
Output /1M
$8
Cached /1M
$0.5
Scores
7 · 7 core
Quality

Benchmark matrix

BenchmarkGPT-5 nanoo3ΔEdge
Reported by both · 6
SWE-bench Verified54.7% 69.1% -14.4 pto3
GPQA Diamond69.4% epoch81.8% epoch-12.4 pto3
AIME 202585% matharena89.2% matharena-4.2 pto3
FrontierMath Tiers 1-3 v2 (Epoch AI run)20% epoch33.3% epoch-13.3 pto3
OTIS Mock AIME 2024-2025 (Epoch AI run)81.1% epoch84.4% epoch-3.3 pto3
SimpleQA Verified11.7% epoch49.4% epoch-37.7 pto3
Only GPT-5 nano reports · 1
FrontierMath Tier 4 v2 (Epoch AI run)2.4% epochnot reported
Only o3 reports · 1
SWE-bench Verified (Epoch AI run)not reported62.3% 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-5 nano minus o3 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-5 nanoo3Edge
Context window400K tokens200K tokensGPT-5 nano
Max output128K tokens100K tokensGPT-5 nano
Input price / 1M$0.05 $2 GPT-5 nano
Output price / 1M$0.4 $8 GPT-5 nano
Cached input / 1M$0.005 $0.5 GPT-5 nano
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$0.45$10GPT-5 nano
Modalitiestext · visiontext · visionTie
Released2025-08-072025-04-16
Cited benchmark scores77
Reliability

OpenAI status

All providers
More matchups

GPT-5 nano vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GPT-5 nano and o3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.