ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Amazon Nova ProvsGPT-4o mini

Amazon Nova Pro leads 1 of 1 shared benchmark. GPT-4o mini is 5.3x cheaper per token. Amazon Nova Pro has the larger context window (300K tokens).

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

Shared benchmarks
1 – 0
Amazon Nova Pro leads
Cheaper per token
GPT-4o mini
5.3x cheaper, input + output
Larger context
Amazon Nova Pro
300K tokens
Provider uptime (30d)
— · 95.5307%
Amazon · OpenAI
Amazon Nova Pro
Amazon · released 2024-12-02
textvision
Context
300K
Max out
10K
Input /1M
$0.8
Output /1M
$3.2
Cached /1M
Scores
8 · 2 core
GPT-4o mini
OpenAI · released 2024-07-18
textvision
Context
128K
Max out
16K
Input /1M
$0.15
Output /1M
$0.6
Cached /1M
$0.075
Scores
7 · 6 core
Quality

Benchmark matrix

BenchmarkAmazon Nova ProGPT-4o miniΔEdge
Reported by both · 1
MMLU85.9% 82% +3.9 ptAmazon Nova Pro
Only Amazon Nova Pro reports · 7
ARC-C94.8% not reported
BBH86.9% not reported
DROP85.4% not reported
GPQA46.9% not reported
GSM8K94.8% not reported
IFEval92.1% not reported
MATH76.6% not reported
Only GPT-4o mini reports · 5
GPQA Diamondnot reported40.2%
AIME 2024not reported8.6%
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported0.7% epoch
OTIS Mock AIME 2024-2025 (Epoch AI run)not reported6.9% epoch
SimpleQA Verifiednot reported8.3% 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 Amazon Nova Pro minus GPT-4o mini 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

SpecAmazon Nova ProGPT-4o miniEdge
Context window300K tokens128K tokensAmazon Nova Pro
Max output10K tokens16K tokensGPT-4o mini
Input price / 1M$0.8 $0.15 GPT-4o mini
Output price / 1M$3.2 $0.6 GPT-4o mini
Cached input / 1M$0.075
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$4$0.75GPT-4o mini
Modalitiestext · visiontext · visionTie
Released2024-12-022024-07-18
Cited benchmark scores87
Reliability

Provider status

All providers
More matchups

Amazon Nova Pro vs …

More matchups

GPT-4o mini vs …

Built by Respan
Which one wins on your data?

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