OpenAI · proprietary

GPT-5.5 Instant

GPT-5.5 Instant by OpenAI appears in 2 sources with Reasoning at 42.54. Best read for Coding, High intelligence, LLM.

CreatorOpenAI

Release date2026-05-05

Knowledge cutoffNot published

Context400K tokens

Input price$5/M tokens

Output price$30/M tokens

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank19ranking · source_rank

LLM Stats Code Index (estimated from arena)43.43 scoremetric

Reasoning42.54reasoning · index_reasoning

Math21.67math · index_math

Vision29.69multimodal · index_vision

Healthcare25.76domain · index_healthcare

GPQA85.6 %reasoning · gpqa_score

AIME 202581.2 %math · aime_2025_score

Code Arena1,360.69 %coding · coding_arena_score

MMMU-Pro76 %multimodal · mmmu_pro_score

CharXiv-R81.6 %multimodal · charxiv_r_score

Context400,000 tokenscontext · context

Speed227.44 c/sperformance · throughput

Latency2,596.63 msperformance · latency

Input price5 $/Mpricing · input_price

Output price30 $/Mpricing · output_price

Arena Rating1,418.36metric

Arena Rank79metric

Vote Count5,874metric

Evidence

Citations and source overlap

Arena AILM Arena text leaderboard (overall) mirrored in the public leaderboard dataset.Retrieved 2026-05-20 LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is GPT-5.5 Instant verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.