VerdictPal
Join

Models / OpenAI

GPT-5.5 (medium)

GPT-5.5 (medium) · Released 2026-04-23

AA Intelligence Index 50.4. Listed on Artificial Analysis with API pricing $5/$30 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#9 of 51 on AA Index · current snapshot
50 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite61
Context128K
Input / 1M$5.0
Output / 1M$30
Knowledge cutoffopen
Output speed76 t/s
TTFT (default API)6.88s
Statussolid
ReasoningCodingAgenticLong context
Reasoning
93
Coding
54
Agentic
81
Long context
72

75average across 4 tested families

Benchmark placements

Where GPT-5.5 (medium) 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
GPQA DiamondReasoning#9/ 6993Artificial Analysis2026-07-21
Terminal-BenchAgentic#11/ 6981Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#12/ 6541Artificial Analysis2026-07-21
AA-LCRLong context#13/ 6472Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#15/ 6750Artificial Analysis2026-07-21
SciCodeCoding#15/ 6554Artificial Analysis2026-07-21
AA time to first tokenPerformance#23/ 69Artificial Analysis2026-07-21
IFBenchReasoning#32/ 5771Artificial Analysis2026-07-21
τ³-Bench BankingAgentic#34/ 6426Artificial Analysis2026-07-21
AA output speedPerformance#36/ 69Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models in each capability family. Where GPT-5.5 (medium) shows up, it's highlighted.

ReasoningGPT-5.5 (medium) · 93
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
CodingGPT-5.5 (medium) · 54
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGPT-5.5 (medium) · 81
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGPT-5.5 (medium) · 72
  1. 1
    Kimi K3
    75
  2. 2
    GPT-5.1
    75
  3. 3
    GPT-5.6 Sol
    74
Newest receipts

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

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context72.33%Artificial Analysis2
AA output speedPerformance76 t/sArtificial Analysis2
AA time to first tokenPerformance6.88sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning50.4%Artificial Analysis2
GPQA DiamondReasoning92.6%Artificial Analysis2
Humanity's Last ExamReasoning40.6%Artificial Analysis2
IFBenchReasoning70.95%Artificial Analysis2
SciCodeCoding53.5%Artificial Analysis2
τ³-Bench BankingAgentic25.77%Artificial Analysis2
Terminal-BenchAgentic80.52%Artificial Analysis2
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.

Reasoning93
Coding54
Agentic81
Long context72
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere

Full benchmark ledger

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

10 sourced rows

10 of 32 catalog benchmarks have a sourced row for GPT-5.5 (medium).

Reasoning

Coding

Agentic

Long context

Performance

Sources