ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GPT-5.4 ProvsGPT-5.5 Pro

GPT-5.5 Pro leads 7 of 8 shared benchmarks. Both list the same combined token price. Both offer a 1.1M-token context window.

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

Shared benchmarks
1 – 7
GPT-5.5 Pro leads
Cheaper per token
Tie
list price, input + output
Larger context
Tie
both 1.1M tokens
Provider uptime (30d)
94.2446%
OpenAI
GPT-5.4 Pro
OpenAI · released 2026-03-05
textvision
Context
1.1M
Max out
128K
Input /1M
$30
Output /1M
$180
Cached /1M
Scores
13 · 8 core
GPT-5.5 Pro
OpenAI · released 2026-04-23
textvision
Context
1.1M
Max out
128K
Input /1M
$30
Output /1M
$180
Cached /1M
Scores
8 · 6 core
Quality

Benchmark matrix

BenchmarkGPT-5.4 ProGPT-5.5 ProΔEdge
Reported by both · 8
Humanity's Last Exam (no tools)42.7% 43.1% -0.4 ptGPT-5.5 Pro
BrowseComp89.3% 90.1% -0.8 ptGPT-5.5 Pro
FrontierMath Tier 1-350% 52.4% -2.4 ptGPT-5.5 Pro
FrontierMath Tier 438% 39.6% -1.6 ptGPT-5.5 Pro
FrontierMath Tier 4 v2 (Epoch AI run)58.5% epoch78% epoch-19.5 ptGPT-5.5 Pro
FrontierMath Tiers 1-3 v2 (Epoch AI run)82.5% epoch87.7% epoch-5.2 ptGPT-5.5 Pro
GDPval (wins or ties)82% 82.3% -0.3 ptGPT-5.5 Pro
Humanity's Last Exam (with tools)58.7% 57.2% +1.5 ptGPT-5.4 Pro
Only GPT-5.4 Pro reports · 4
GPQA Diamond94.4% not reported
ARC-AGI-1 (Verified)94.5% not reported
ARC-AGI-2 (Verified)83.3% not reported
SimpleQA Verified46.3% epochnot reported
Only GPT-5.5 Pro reports · 0
GPT-5.5 Pro reports nothing GPT-5.4 Pro does not.
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-5.4 Pro minus GPT-5.5 Pro 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-5.4 ProGPT-5.5 ProEdge
Context window1.1M tokens1.1M tokensTie
Max output128K tokens128K tokensTie
Input price / 1M$30 $30 Tie
Output price / 1M$180 $180 Tie
Cached input / 1M
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$210$210Tie
Modalitiestext · visiontext · visionTie
Released2026-03-052026-04-23
Cited benchmark scores138
Reliability

OpenAI status

All providers
More matchups

GPT-5.4 Pro vs …

More matchups

GPT-5.5 Pro vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GPT-5.4 Pro and GPT-5.5 Pro on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.