whatmodel.sh / GPT-5.5 Instant

GPT-5.5 Instant

+ contribute

GPT-5.5 Instant is a closed-weights language model from OpenAI, released May 2026.

Catalogue identity notes

Comparison-only. Epoch model_metadata.csv: model_version gpt-5.5-instant, group 'GPT-5.5 Instant', OpenAI, date 2026-05-05, accessibility 'API access'. Arena entry 'gpt-5.5-instant' (openai, Proprietary), first listed 2026-05-06. Distinct from gpt-5-5 (GPT-5.5 reasoning model).

68.7±1.0comparison only: no current run option verifiedfrom 9 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of GPT-5.5 Instant, out of 828 with a score, then more from OpenAI.

#	model	score	where	RAM	released
106	Gemini 3.5 Flash-Lite Google	69±1	api $0.85/M		2026-07
107	GLM-4.7 Z.ai	69±1	api $1.00/M +local	~58GB	2025-12
108	GPT-5.5 Instant OpenAI	69±1	comparison only		2026-05
109	GPT-5.4 nano OpenAI	69±1	api $0.46/M		2026-03
110	Claude Sonnet 4.5 Anthropic	69±1	api $6.00/M		2025-09
	more from OpenAI
1	GPT-6 Astra OpenAI	87±1	api $20.00/M		2026-09
3	GPT-6.1 Sol OpenAI	85±1	api $4.00/M		2026-09
7	GPT-6 Sol OpenAI	83±1	api $4.00/M		2026-09

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #32 of 463 * · 9.2% of its score · 1 test

Beats Claude Sonnet 5.5, GPT-6 Sol, GPT-5.6 Terra here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
LMArena (text)	1473.3 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 347/379	avg 1268	▇▇▇▇ 9.2%	blunt

math▁▂▃▅▇▅▅█▄▁▁▁ #138 of 462 · 59% of its score · 3 tests

Beats Claude Sonnet 4.6, MiniMax-M3, MiMo-V2.5 (310B-A15B) here, though they rank higher overall. Trails Olmo 3.1 32B Think, Qwen3-VL 30B-A3B Thinking, Granite 4.2 8B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
FrontierMath tiers 1–3 v2	26.3% ✎	▂··▁▁▃▄▄█▅▃▃ beats 18/82	very hard · avg 1.2%	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 41%	sharp · at its level
FrontierMath tier 4 v2	2.4% ✎	▁▃▁▂█▅▂▂▁▁▁▁ beats 5/63	very hard · avg 0.1%	▇▇▇▇▇ 13%	sharp
OTIS mock AIME 2024–2025	68.1% ✎	▃▃▄▃▃▃▇▇█▃▂▅ beats 98/193	very hard · avg 8.5%	▇▇ 5.3%	sharp · noisy

vision & documents▁▁▃▃▂▃▅▄▇▇█▃ #30 of 182 · 15% of its score · 3 tests

Beats Claude Sonnet 5.5, MiMo-V2.6-Pro, GPT-5.6 Terra here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Arena vision (style controlled)	1276.0 ✎	▁▁▂▂▂▂▄▅▅▆██ beats 120/145	avg 1068	▇▇▇ 6.4%	blunt
CharXiv (reasoning questions) lab	81.6% ✎	▄··▂█··▂···▄ beats 8/9	hard · avg 34%	▇▇ 5.3%	at its level
Arena document (style controlled)	1460.3 ✎	▁▁▃▃▄▃▇█▅▇▄▅ beats 17/37	avg 1335	▇ 3.1%	blunt

other tests2 not in a task · 17% of its score

test	result	vs the others in its run	difficulty	counts	why
GPQA Diamond	82.5% ✎	▁▁▁▁▂▄▆▄▅▇█▅ beats 135/208	hard · avg 40%	▇▇▇▇▇ 12%	sharp
Chess Puzzles (Epoch)	12.0% ✎	█▁▁▁▁▃▁▄▂▂▁▁ beats 56/135	very hard · avg 5.9%	▇▇ 4.4%	sharp · noisy

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · Epoch AI — internal evaluatio… 76%, LMArena leaderboard dataset 19%, OpenAI vendor-reported benchm… 5%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
Epoch AI — internal evaluations	5	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 76%	CC BY 4.0
LMArena leaderboard dataset	3	▇▇▇▇▇▇ 19%	CC BY 4.0
OpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards) · lab-reported	1	▇▇ 5%	Factual vendor-reported score (not licensed content)
prior · pull toward the middle		▇ 0%
weighted average		= 68.7