VerdictPal
Join

Models / OpenAI

GPT-5.5 Instant (June 2026)

GPT-5.5 Instant · Released 2026-06-25

AA Intelligence Index 28.9. 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.

#70 of 184 on AA Index · current snapshot
27 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite42
ContextUnlisted
Input / 1M$5.0
Output / 1M$30
Knowledge cutoffunpublished
Output speed145 t/s
TTFT (default API)0.88s
Statussolid

Family profile

Best published score in each covered benchmark family.

60/100 avg
Reasoning
82
Coding
53
Agentic
35
Long context
70

4 tested benchmark families

Benchmark placements

Where GPT-5.5 Instant (June 2026) 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
AA output speedPerformance#17/ 190Artificial Analysis2026-09-10
SciCodeCoding#30/ 9353Artificial Analysis2026-09-10
AA time to first tokenPerformance#69/ 190Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#72/ 18827Artificial Analysis2026-09-10
τ³-Bench BankingAgentic#91/ 11012Artificial Analysis2026-09-10
AA-LCRLong context#120/ 18270Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#126/ 18520Artificial Analysis2026-09-10
GPQA DiamondReasoning#130/ 19082Artificial Analysis2026-09-10
Terminal-BenchAgentic#141/ 18935Artificial Analysis2026-09-10
Family context

The three highest-scoring models with pages in each capability family. Where GPT-5.5 Instant (June 2026) shows up, it's highlighted.

ReasoningGPT-5.5 Instant (June 2026) · 82
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
CodingGPT-5.5 Instant (June 2026) · 53
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGPT-5.5 Instant (June 2026) · 35
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGPT-5.5 Instant (June 2026) · 70
  1. 1
    Kimi K3
    89
  2. 2
    Claude Fable 5.1
    85
  3. 3
    GPT-5.5 (high)
    84
Newest receipts

Benchmark rows added to the public ledger for GPT-5.5 Instant (June 2026) in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context70%Artificial Analysis4
AA output speedPerformance145 t/sArtificial Analysis4
AA time to first tokenPerformance0.88sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning26.8%Artificial Analysis4
GPQA DiamondReasoning82.3%Artificial Analysis4
Humanity's Last ExamReasoning19.9%Artificial Analysis4
SciCodeCoding52.5%Artificial Analysis4
τ³-Bench BankingAgentic11.75%Artificial Analysis4
Terminal-BenchAgentic34.83%Artificial Analysis4
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.

Reasoning82
Coding53
Agentic35
Long context70
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for GPT-5.5 Instant (June 2026). Scores link to the original source; gaps mean no public row exists yet.

9 sourced rows

9 of 37 catalog benchmarks have a sourced row for GPT-5.5 Instant (June 2026).

Reasoning

Coding

Agentic

Long context

Performance

Sources