Models / GPT-5.5 Instant

OpenAI

GPT-5.5 Instant

GPT-5.5 Instant is best for writing; it is not on sale through OpenRouter, so it is here for reference.

Results 16 Nov 2026 · 26 results · 2 sources

Price per million tokens
Not available through OpenRouter
Speed
152 tokens a second; on its test prompt the answer starts after 13.9 s, thinking time included
Artificial Analysis, on its usual API, at 2026-06-26
Intelligence Index
26.0
Artificial Analysis, at 2026-06-26; 22.7–26.0 across 2 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
OpenAI, based in the US
Weights not published
Released
5 May 2026

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 68th of 186Claude Opus 5.5 – – 22nd of 66Nemotron 3.5 Super VL
Models with similar intelligence sets this group – – 5th of 11Nemotron 3.5 Super VL
Models writing 100–200 tokens a second 13th of 22Claude Sonnet 5.5 – – sets this group
Models from developers based in the US 42nd of 93Claude Opus 5.5 – – 14th of 34Nemotron 3.5 Super VL

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 89th of 160 available
BenchmarkGPT-5.5 InstantRank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 12.6% 35th of 108 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 34.8% 75th of 108 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 11.8% 67th of 105 Grok 4.6 50.7%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 87th of 188 available
BenchmarkGPT-5.5 InstantRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 26.0 68th of 186 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 21.6% 98th of 187 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 84.6% 73rd of 169 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 30th of 170 available
BenchmarkGPT-5.5 InstantRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,473 29th of 154 Gemini 4 Argon 1,525
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers 77th of 140 available
BenchmarkGPT-5.5 InstantRank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,444 61st of 110 Gemini 4 Argon 1,511
  • Vectara Hallucination Leaderboard: has not measured this model.
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against GPT-5.5 Instant, Intelligence Index 26.0. "Similar intelligence" means within 4 points or better.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

GPT-5.5 InstantNemotron 3.5 Super VL
fastest with similar intelligence
Claude Opus 5.5
most intelligent available today
Claude Fable 5.2
leads overall
GPT-6.1 Sol
OpenAI's best other model
Price per million tokens – $0.24$8.00$16.00$4.00
Tokens a second 152 41196–53
Intelligence Index 26.0 26.557.6–51.8
Spring Prompt overall – –829080
Rank among available models, by use case
Product listings – –13th5th2nd
Decks from an analysis – –7th4th5th
User surveys – –4th1st3rd
Marketing planning – –9th1st–
Agents and tool use 89th of 160 133rd3rd–6th
Professional work – –3rd–9th
Reasoning and knowledge 87th of 188 74th1st–6th
Writing 30th of 170 –5th–16th
Sticking to the facts 77th of 140 –3rd–18th
Speed under pressure – ––8th3rd

Shaded figures are better than GPT-5.5 Instant's. A dash means no result.

Where it has been measured

Compared with the models available today (it is not on sale itself), in the top quarter (by percentile) for writing.

Every result

26 published results from 2 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 8 results
MeasureValueRankConfigurationDated
Arena Document: overallArena rating, higher is better 1,460
1,452–1,469
26 of 44 GPT-5.5 Instant 13 Sep 2026
Arena Text factuality: overallArena rating, higher is better 1,444
1,439–1,448
86 of 182 GPT-5.5 Instant 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,476
1,467–1,485
29 of 406 GPT-5.5 Instant 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,456
1,447–1,466
30 of 411 GPT-5.5 Instant 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,473
1,461–1,485
83 of 363 GPT-5.5 Instant 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,456
1,449–1,463
55 of 413 GPT-5.5 Instant 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,473
1,468–1,478
40 of 413 GPT-5.5 Instant 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,461
1,453–1,469
36 of 412 GPT-5.5 Instant 2 Oct 2026

Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Artificial Analysis · reported by Artificial Analysis · 18 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 39.4 121 of 187 GPT-5.5 Instant (2026-06-26) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 22.7 182 of 413 GPT-5.5 Instant (2026-05-26) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 26.0 146 of 413 GPT-5.5 Instant (2026-06-26) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 84.6% 126 of 360 GPT-5.5 Instant (2026-05-26) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 82.3% 156 of 360 GPT-5.5 Instant (2026-06-26) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 21.6% 192 of 419 GPT-5.5 Instant (2026-05-26) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 19.9% 201 of 419 GPT-5.5 Instant (2026-06-26) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 71.5% 49 of 288 GPT-5.5 Instant (2026-05-26) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 66.3% 226 of 407 GPT-5.5 Instant (2026-05-26) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 70.0% 199 of 407 GPT-5.5 Instant (2026-06-26) 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 152 37 of 137 GPT-5.5 Instant (2026-06-26) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 52.5% 84 of 205 GPT-5.5 Instant (2026-06-26) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 34.8% 130 of 188 GPT-5.5 Instant (2026-06-26) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 12.6% 86 of 204 GPT-5.5 Instant (2026-06-26) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 42.4% 45 of 282 GPT-5.5 Instant (2026-05-26) 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 13.9 70 of 137 GPT-5.5 Instant (2026-06-26) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 11.8% 117 of 175 GPT-5.5 Instant (2026-06-26) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 49.4% 164 of 286 GPT-5.5 Instant (2026-05-26) 20 Oct 2026

Not shown: Not your codebase or tools.

Test your own prompt.

Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.