VerdictPal
Join

Models / OpenAI

GPT-5.5 Pro

GPT 5 · Released 2026-04-23

OpenAI's premium GPT-5.5 tier. GDPval 82.3% (wins or ties). 1.05M context, $30 / $180 per 1M tokens. Responses API only — higher reasoning ceiling than standard GPT-5.5.

OpenAI Pro-tier pick when accuracy matters more than latency — legal, finance, and multi-pass research workflows.

Composite54
Context1M
Input / 1M$30
Output / 1M$180
Knowledge cutoff2025-12-01
Statussolid
ChatGPT

Family profile

Best published score in each covered benchmark family.

55/100 avg
Reasoning
31
Math
52
Agentic
82

3 tested benchmark families

Benchmark placements

Where GPT-5.5 Pro places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
FrontierMathMath#1/ 1552Epoch AI FrontierMath Tiers 1-3 (v2) CSV2026-08-15
CritPtReasoning#2/ 1231Artificial Analysis — CritPt2026-09-01
GDPvalAgentic#4/ 682OpenAI GDPval grading portal2026-04-23
AA time to first tokenPerformance#143/ 186Artificial Analysis2026-09-01
AA output speedPerformance#144/ 187Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where GPT-5.5 Pro shows up, it's highlighted.

ReasoningGPT-5.5 Pro · 31
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
MathGPT-5.5 Pro · 52
  1. 1
    OpenAI o3
    99
  2. 2
    GPT-5 (medium)
    99
  3. 3
    GPT-5 (high)
    99
AgenticGPT-5.5 Pro · 82
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Newest receipts

Benchmark rows added to the public ledger for GPT-5.5 Pro in the last 120 days. Older rows live in the full table below.

4 recent
BenchmarkFamilyScoreSourceDays ago
CritPtReasoning30.6%Artificial Analysis — CritPt5
AA output speedPerformance0 t/sArtificial Analysis5
AA time to first tokenPerformance0.00sArtificial Analysis5
FrontierMathMath52.4%Epoch AI FrontierMath Tiers 1-3 (v2) CSV22
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning31
Math52
Agentic82
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for GPT-5.5 Pro. Scores link to the original source; gaps mean no public row exists yet.

5 sourced rows

5 of 37 catalog benchmarks have a sourced row for GPT-5.5 Pro.

Reasoning

Math

Agentic

Performance

Changelog
  1. Released GPT-5.5 Pro — premium tier, $30/$180, Responses API.
Sources