ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GPT-5vsGPT-5.2

GPT-5.2 leads 7 of 8 shared benchmarks. GPT-5 is 1.4x 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
1 – 7
GPT-5.2 leads
Cheaper per token
GPT-5
1.4x cheaper, input + output
Larger context
Tie
both 400K tokens
Provider uptime (30d)
95.0311%
OpenAI
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
GPT-5.2
OpenAI · released 2025-12-11
textvision
Context
400K
Max out
128K
Input /1M
$1.75
Output /1M
$14
Cached /1M
$0.175
Scores
16 · 11 core
Quality

Benchmark matrix

BenchmarkGPT-5GPT-5.2ΔEdge
Reported by both · 8
SWE-bench Verified74.9% 80% -5.1 ptGPT-5.2
GPQA Diamond86.2% epoch92.4% -6.2 ptGPT-5.2
AIME 202594.6% 100% -5.4 ptGPT-5.2
FrontierMath Tier 4 v2 (Epoch AI run)22% epoch31.7% epoch-9.7 ptGPT-5.2
FrontierMath Tiers 1-3 v2 (Epoch AI run)55.4% epoch67.4% epoch-12 ptGPT-5.2
OTIS Mock AIME 2024-2025 (Epoch AI run)91.4% epoch96.1% epoch-4.7 ptGPT-5.2
SimpleQA Verified50.1% epoch37.1% epoch+13 ptGPT-5
SWE-bench Verified (Epoch AI run)73.6% epoch73.8% epoch-0.2 ptGPT-5.2
Only GPT-5 reports · 0
GPT-5 reports nothing GPT-5.2 does not.
Only GPT-5.2 reports · 6
AIME 2026not reported98.3% matharena
LMArena Elonot reported1412.4
ARC-AGI-1 (Verified)not reported86.2%
ARC-AGI-2 (Verified)not reported52.9%
GDPval (wins or ties)not reported70.9%
SWE-Bench Pronot reported55.6%
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 minus GPT-5.2 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-5GPT-5.2Edge
Context window400K tokens400K tokensTie
Max output128K tokens128K tokensTie
Input price / 1M$1.25 $1.75 GPT-5
Output price / 1M$10 $14 GPT-5
Cached input / 1M$0.125 $0.175 GPT-5
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$11.25$15.75GPT-5
Modalitiestext · visiontext · visionTie
Released2025-08-072025-12-11
Cited benchmark scores916
Reliability

OpenAI status

All providers
Built by Respan
Which one wins on your data?

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