GPT-5.5 Pro
GPT-5.5 Pro is capable in reasoning and math. Too few results yet to rate coding, agentic tasks, safety, long context, multimodal tasks, multilingual tasks, instruction following, or factuality.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Coding, Agentic, Safety, Long Context, Multimodal, Multilingual, Instruction Following or Factuality.
Price
$30.00input$180.00outputper million tokens
From openai · All prices
Evidence
16results on14benchmarks
- 9 independently verified
- 1 aggregator
- 6 vendor-reported
From 9 sources · latest Oct 8, 2026 · How verification works
API features
Tool callingStructured outputsReasoning
As listed by OpenRouter
Research
6 papers reference GPT-5.5 ProGPT-5.5 Pro benchmark results
16 results on 14 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
10.6% behind the leader4 of 6 ranked benchmarks measured
- 30.57Oct 8, 2026
- 84.16Sep 21, 2026
- 57.20Oct 7, 2026
- 76.90May 10, 2026
Show 1 more reasoning resultHide 1 reasoning result
- 84.58May 10, 2026
21.7% behind the leader2 of 5 ranked benchmarks measured
- 87.72Sep 21, 2026
- 78.05Sep 21, 2026
0 of 7 ranked benchmarks measured
- 90.10Oct 7, 2026
0 of 4 ranked benchmarks measured
- 64.50May 20, 2026
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- 95.00Sep 21, 2026
- frontiermath_tier_4_v139.60Aug 29, 2026frontiermath_tier_4
- 96.50May 10, 2026
- FrontierMath (overall)39.60Oct 7, 2026FrontierMath
- 33.20Oct 7, 2026
- 0.00Aug 11, 2026
Show 1 more resultHide 1 result
- 16.50Jul 7, 2026
GPT-5.5 Pro: common questions
Who makes GPT-5.5 Pro?
GPT-5.5 Pro is made by OpenAI.
When was GPT-5.5 Pro released?
GPT-5.5 Pro was released on Apr 23, 2026, according to Artificial Analysis.
What is GPT-5.5 Pro good at?
GPT-5.5 Pro is capable in reasoning and math. Too few results yet to rate coding, agentic tasks, safety, long context, multimodal tasks, multilingual tasks, instruction following, or factuality.
How much does GPT-5.5 Pro cost?
GPT-5.5 Pro costs $30.00 per million input tokens and $180.00 per million output tokens, according to openai. At a mix of three input tokens to one output token, it costs more than 99% of the 330 priced models we track.
How many benchmarks has GPT-5.5 Pro been tested on?
We track 16 results for GPT-5.5 Pro on 14 benchmarks from 9 sources, 9 of them independently verified. The latest was recorded on Oct 8, 2026.
Which API features does GPT-5.5 Pro support?
OpenRouter lists tool calling, structured outputs, and reasoning for GPT-5.5 Pro.
About this record
Where GPT-5.5 Pro's numbers come from, and every name it appears under.
- Tracked since
- Apr 26, 2026
- Newest source mention
- May 10, 2026
Where the results come from
Verification: 16 scores · 9 independently verified · 1 aggregator-attributed · 6 vendor-reported. How these tiers are assigned
From 9 sources on 6 sites. api.llm-stats.com supplies 4 of them; the 9 independently verified results come from 3 sites. Bars are coloured by trust tier.
- api.llm-stats.com4
- arcprize.org4
- epoch.ai4
- deploymentsafety.openai.com2
- artificialanalysis.ai1
- simple-bench.com1
Also known as
How our sources name GPT-5.5 Pro at each reasoning setting.
| Setting | Short form |
|---|---|
| high | gpt-5.5 pro (high) |
| xhigh | gpt-5.5 pro (xhigh) |