ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GPT-5.2 ProvsGPT-5 mini

GPT-5.2 Pro leads 4 of 4 shared benchmarks. GPT-5 mini is 84x cheaper per token. Both offer a 400K-token context window.

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

Shared benchmarks
4 – 0
GPT-5.2 Pro leads
Cheaper per token
GPT-5 mini
84x cheaper, input + output
Larger context
Tie
both 400K tokens
Provider uptime (30d)
94.2446%
OpenAI
GPT-5.2 Pro
OpenAI · released 2025-12-11
textvision
Context
400K
Max out
128K
Input /1M
$21
Output /1M
$168
Cached /1M
Scores
10 · 6 core
GPT-5 mini
OpenAI · released 2025-08-07
textvision
Context
400K
Max out
128K
Input /1M
$0.25
Output /1M
$2
Cached /1M
$0.025
Scores
9 · 8 core
Quality

Benchmark matrix

BenchmarkGPT-5.2 ProGPT-5 miniΔEdge
Reported by both · 4
GPQA Diamond93.2% 81.6% +11.6 ptGPT-5.2 Pro
AIME 2025100% 87.5% matharena+12.5 ptGPT-5.2 Pro
FrontierMath Tier 4 v2 (Epoch AI run)46% epoch12.2% epoch+33.8 ptGPT-5.2 Pro
FrontierMath Tiers 1-3 v2 (Epoch AI run)74% epoch46.7% epoch+27.3 ptGPT-5.2 Pro
Only GPT-5.2 Pro reports · 6
Humanity's Last Exam (no tools)36.6% not reported
ARC-AGI-1 (Verified)90.5% not reported
ARC-AGI-2 (Verified)54.2% not reported
BrowseComp77.9% not reported
GDPval (wins or ties)74.1% not reported
Humanity's Last Exam (with tools)50% not reported
Only GPT-5 mini reports · 4
SWE-bench Verifiednot reported71%
OTIS Mock AIME 2024-2025 (Epoch AI run)not reported86.7% epoch
SimpleQA Verifiednot reported21.6% epoch
SWE-bench Verified (Epoch AI run)not reported64.7% 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-5.2 Pro minus GPT-5 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

SpecGPT-5.2 ProGPT-5 miniEdge
Context window400K tokens400K tokensTie
Max output128K tokens128K tokensTie
Input price / 1M$21 $0.25 GPT-5 mini
Output price / 1M$168 $2 GPT-5 mini
Cached input / 1M$0.025
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$189$2.25GPT-5 mini
Modalitiestext · visiontext · visionTie
Released2025-12-112025-08-07
Cited benchmark scores109
Reliability

OpenAI status

All providers
More matchups

GPT-5.2 Pro vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GPT-5.2 Pro and GPT-5 mini on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.