ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GPT-4.1 nanovsGPT-5

GPT-5 leads 3 of 3 shared benchmarks. GPT-4.1 nano is 22.5x cheaper per token. GPT-4.1 nano has the larger context window (1.0M tokens).

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

Shared benchmarks
0 – 3
GPT-5 leads
Cheaper per token
GPT-4.1 nano
22.5x cheaper, input + output
Larger context
GPT-4.1 nano
1.0M tokens
Provider uptime (30d)
94.2446%
OpenAI
GPT-4.1 nano
OpenAI · released 2025-04-14
textvision
Context
1.0M
Max out
33K
Input /1M
$0.1
Output /1M
$0.4
Cached /1M
$0.025
Scores
7 · 5 core
GPT-5
OpenAI · released 2025-08-07
textvision
Context
400K
Max out
128K
Input /1M
$1.25
Output /1M
$10
Cached /1M
$0.125
Scores
9 · 8 core
Quality

Benchmark matrix

BenchmarkGPT-4.1 nanoGPT-5ΔEdge
Reported by both · 3
GPQA Diamond50.3% 86.2% epoch-35.9 ptGPT-5
OTIS Mock AIME 2024-2025 (Epoch AI run)28.9% epoch91.4% epoch-62.5 ptGPT-5
SimpleQA Verified6% epoch50.1% epoch-44.1 ptGPT-5
Only GPT-4.1 nano reports · 3
MMLU80.1% not reported
Aider Polyglot9.8% not reported
AIME 202429.4% not reported
Only GPT-5 reports · 5
SWE-bench Verifiednot reported74.9%
AIME 2025not reported94.6%
FrontierMath Tier 4 v2 (Epoch AI run)not reported22% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported55.4% epoch
SWE-bench Verified (Epoch AI run)not reported73.6% 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-4.1 nano minus GPT-5 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-4.1 nanoGPT-5Edge
Context window1.0M tokens400K tokensGPT-4.1 nano
Max output33K tokens128K tokensGPT-5
Input price / 1M$0.1 $1.25 GPT-4.1 nano
Output price / 1M$0.4 $10 GPT-4.1 nano
Cached input / 1M$0.025 $0.125 GPT-4.1 nano
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$0.5$11.25GPT-4.1 nano
Modalitiestext · visiontext · visionTie
Released2025-04-142025-08-07
Cited benchmark scores79
Reliability

OpenAI status

All providers
More matchups

GPT-4.1 nano vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GPT-4.1 nano and GPT-5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.